- 4.14.189

[packages/kernel.git] / kernel-rt.patch

diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index 2cc08d4a326e..e28f7f29f2b3 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -517,1550 +517,4 @@ The following commands are supported:
   totals derived from one or more trace event format fields and/or
   event counts (hitcount).
 
-  The format of a hist trigger is as follows:
-
-        hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
-          [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
-          [:clear][:name=histname1] [if <filter>]
-
-  When a matching event is hit, an entry is added to a hash table
-  using the key(s) and value(s) named.  Keys and values correspond to
-  fields in the event's format description.  Values must correspond to
-  numeric fields - on an event hit, the value(s) will be added to a
-  sum kept for that field.  The special string 'hitcount' can be used
-  in place of an explicit value field - this is simply a count of
-  event hits.  If 'values' isn't specified, an implicit 'hitcount'
-  value will be automatically created and used as the only value.
-  Keys can be any field, or the special string 'stacktrace', which
-  will use the event's kernel stacktrace as the key.  The keywords
-  'keys' or 'key' can be used to specify keys, and the keywords
-  'values', 'vals', or 'val' can be used to specify values.  Compound
-  keys consisting of up to two fields can be specified by the 'keys'
-  keyword.  Hashing a compound key produces a unique entry in the
-  table for each unique combination of component keys, and can be
-  useful for providing more fine-grained summaries of event data.
-  Additionally, sort keys consisting of up to two fields can be
-  specified by the 'sort' keyword.  If more than one field is
-  specified, the result will be a 'sort within a sort': the first key
-  is taken to be the primary sort key and the second the secondary
-  key.  If a hist trigger is given a name using the 'name' parameter,
-  its histogram data will be shared with other triggers of the same
-  name, and trigger hits will update this common data.  Only triggers
-  with 'compatible' fields can be combined in this way; triggers are
-  'compatible' if the fields named in the trigger share the same
-  number and type of fields and those fields also have the same names.
-  Note that any two events always share the compatible 'hitcount' and
-  'stacktrace' fields and can therefore be combined using those
-  fields, however pointless that may be.
-
-  'hist' triggers add a 'hist' file to each event's subdirectory.
-  Reading the 'hist' file for the event will dump the hash table in
-  its entirety to stdout.  If there are multiple hist triggers
-  attached to an event, there will be a table for each trigger in the
-  output.  The table displayed for a named trigger will be the same as
-  any other instance having the same name. Each printed hash table
-  entry is a simple list of the keys and values comprising the entry;
-  keys are printed first and are delineated by curly braces, and are
-  followed by the set of value fields for the entry.  By default,
-  numeric fields are displayed as base-10 integers.  This can be
-  modified by appending any of the following modifiers to the field
-  name:
-
-        .hex        display a number as a hex value
-       .sym        display an address as a symbol
-       .sym-offset display an address as a symbol and offset
-       .syscall    display a syscall id as a system call name
-       .execname   display a common_pid as a program name
-
-  Note that in general the semantics of a given field aren't
-  interpreted when applying a modifier to it, but there are some
-  restrictions to be aware of in this regard:
-
-    - only the 'hex' modifier can be used for values (because values
-      are essentially sums, and the other modifiers don't make sense
-      in that context).
-    - the 'execname' modifier can only be used on a 'common_pid'.  The
-      reason for this is that the execname is simply the 'comm' value
-      saved for the 'current' process when an event was triggered,
-      which is the same as the common_pid value saved by the event
-      tracing code.  Trying to apply that comm value to other pid
-      values wouldn't be correct, and typically events that care save
-      pid-specific comm fields in the event itself.
-
-  A typical usage scenario would be the following to enable a hist
-  trigger, read its current contents, and then turn it off:
-
-  # echo 'hist:keys=skbaddr.hex:vals=len' > \
-    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
-  # echo '!hist:keys=skbaddr.hex:vals=len' > \
-    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  The trigger file itself can be read to show the details of the
-  currently attached hist trigger.  This information is also displayed
-  at the top of the 'hist' file when read.
-
-  By default, the size of the hash table is 2048 entries.  The 'size'
-  parameter can be used to specify more or fewer than that.  The units
-  are in terms of hashtable entries - if a run uses more entries than
-  specified, the results will show the number of 'drops', the number
-  of hits that were ignored.  The size should be a power of 2 between
-  128 and 131072 (any non- power-of-2 number specified will be rounded
-  up).
-
-  The 'sort' parameter can be used to specify a value field to sort
-  on.  The default if unspecified is 'hitcount' and the default sort
-  order is 'ascending'.  To sort in the opposite direction, append
-  .descending' to the sort key.
-
-  The 'pause' parameter can be used to pause an existing hist trigger
-  or to start a hist trigger but not log any events until told to do
-  so.  'continue' or 'cont' can be used to start or restart a paused
-  hist trigger.
-
-  The 'clear' parameter will clear the contents of a running hist
-  trigger and leave its current paused/active state.
-
-  Note that the 'pause', 'cont', and 'clear' parameters should be
-  applied using 'append' shell operator ('>>') if applied to an
-  existing trigger, rather than via the '>' operator, which will cause
-  the trigger to be removed through truncation.
-
-- enable_hist/disable_hist
-
-  The enable_hist and disable_hist triggers can be used to have one
-  event conditionally start and stop another event's already-attached
-  hist trigger.  Any number of enable_hist and disable_hist triggers
-  can be attached to a given event, allowing that event to kick off
-  and stop aggregations on a host of other events.
-
-  The format is very similar to the enable/disable_event triggers:
-
-      enable_hist:<system>:<event>[:count]
-      disable_hist:<system>:<event>[:count]
-
-  Instead of enabling or disabling the tracing of the target event
-  into the trace buffer as the enable/disable_event triggers do, the
-  enable/disable_hist triggers enable or disable the aggregation of
-  the target event into a hash table.
-
-  A typical usage scenario for the enable_hist/disable_hist triggers
-  would be to first set up a paused hist trigger on some event,
-  followed by an enable_hist/disable_hist pair that turns the hist
-  aggregation on and off when conditions of interest are hit:
-
-  # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
-    /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
-    /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
-  # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
-    /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
-  The above sets up an initially paused hist trigger which is unpaused
-  and starts aggregating events when a given program is executed, and
-  which stops aggregating when the process exits and the hist trigger
-  is paused again.
-
-  The examples below provide a more concrete illustration of the
-  concepts and typical usage patterns discussed above.
-
-
-6.2 'hist' trigger examples
----------------------------
-
-  The first set of examples creates aggregations using the kmalloc
-  event.  The fields that can be used for the hist trigger are listed
-  in the kmalloc event's format file:
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
-    name: kmalloc
-    ID: 374
-    format:
-       field:unsigned short common_type;       offset:0;       size:2; signed:0;
-       field:unsigned char common_flags;       offset:2;       size:1; signed:0;
-       field:unsigned char common_preempt_count;               offset:3;       size:1; signed:0;
-       field:int common_pid;                                   offset:4;       size:4; signed:1;
-
-       field:unsigned long call_site;                          offset:8;       size:8; signed:0;
-       field:const void * ptr;                                 offset:16;      size:8; signed:0;
-       field:size_t bytes_req;                                 offset:24;      size:8; signed:0;
-       field:size_t bytes_alloc;                               offset:32;      size:8; signed:0;
-       field:gfp_t gfp_flags;                                  offset:40;      size:4; signed:0;
-
-  We'll start by creating a hist trigger that generates a simple table
-  that lists the total number of bytes requested for each function in
-  the kernel that made one or more calls to kmalloc:
-
-    # echo 'hist:key=call_site:val=bytes_req' > \
-            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-  This tells the tracing system to create a 'hist' trigger using the
-  call_site field of the kmalloc event as the key for the table, which
-  just means that each unique call_site address will have an entry
-  created for it in the table.  The 'val=bytes_req' parameter tells
-  the hist trigger that for each unique entry (call_site) in the
-  table, it should keep a running total of the number of bytes
-  requested by that call_site.
-
-  We'll let it run for awhile and then dump the contents of the 'hist'
-  file in the kmalloc event's subdirectory (for readability, a number
-  of entries have been omitted):
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-    { call_site: 18446744072106379007 } hitcount:          1  bytes_req:        176
-    { call_site: 18446744071579557049 } hitcount:          1  bytes_req:       1024
-    { call_site: 18446744071580608289 } hitcount:          1  bytes_req:      16384
-    { call_site: 18446744071581827654 } hitcount:          1  bytes_req:         24
-    { call_site: 18446744071580700980 } hitcount:          1  bytes_req:          8
-    { call_site: 18446744071579359876 } hitcount:          1  bytes_req:        152
-    { call_site: 18446744071580795365 } hitcount:          3  bytes_req:        144
-    { call_site: 18446744071581303129 } hitcount:          3  bytes_req:        144
-    { call_site: 18446744071580713234 } hitcount:          4  bytes_req:       2560
-    { call_site: 18446744071580933750 } hitcount:          4  bytes_req:        736
-    .
-    .
-    .
-    { call_site: 18446744072106047046 } hitcount:         69  bytes_req:       5576
-    { call_site: 18446744071582116407 } hitcount:         73  bytes_req:       2336
-    { call_site: 18446744072106054684 } hitcount:        136  bytes_req:     140504
-    { call_site: 18446744072106224230 } hitcount:        136  bytes_req:      19584
-    { call_site: 18446744072106078074 } hitcount:        153  bytes_req:       2448
-    { call_site: 18446744072106062406 } hitcount:        153  bytes_req:      36720
-    { call_site: 18446744071582507929 } hitcount:        153  bytes_req:      37088
-    { call_site: 18446744072102520590 } hitcount:        273  bytes_req:      10920
-    { call_site: 18446744071582143559 } hitcount:        358  bytes_req:        716
-    { call_site: 18446744072106465852 } hitcount:        417  bytes_req:      56712
-    { call_site: 18446744072102523378 } hitcount:        485  bytes_req:      27160
-    { call_site: 18446744072099568646 } hitcount:       1676  bytes_req:      33520
-
-    Totals:
-        Hits: 4610
-        Entries: 45
-        Dropped: 0
-
-  The output displays a line for each entry, beginning with the key
-  specified in the trigger, followed by the value(s) also specified in
-  the trigger.  At the beginning of the output is a line that displays
-  the trigger info, which can also be displayed by reading the
-  'trigger' file:
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-    hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-  At the end of the output are a few lines that display the overall
-  totals for the run.  The 'Hits' field shows the total number of
-  times the event trigger was hit, the 'Entries' field shows the total
-  number of used entries in the hash table, and the 'Dropped' field
-  shows the number of hits that were dropped because the number of
-  used entries for the run exceeded the maximum number of entries
-  allowed for the table (normally 0, but if not a hint that you may
-  want to increase the size of the table using the 'size' parameter).
-
-  Notice in the above output that there's an extra field, 'hitcount',
-  which wasn't specified in the trigger.  Also notice that in the
-  trigger info output, there's a parameter, 'sort=hitcount', which
-  wasn't specified in the trigger either.  The reason for that is that
-  every trigger implicitly keeps a count of the total number of hits
-  attributed to a given entry, called the 'hitcount'.  That hitcount
-  information is explicitly displayed in the output, and in the
-  absence of a user-specified sort parameter, is used as the default
-  sort field.
-
-  The value 'hitcount' can be used in place of an explicit value in
-  the 'values' parameter if you don't really need to have any
-  particular field summed and are mainly interested in hit
-  frequencies.
-
-  To turn the hist trigger off, simply call up the trigger in the
-  command history and re-execute it with a '!' prepended:
-
-    # echo '!hist:key=call_site:val=bytes_req' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-  Finally, notice that the call_site as displayed in the output above
-  isn't really very useful.  It's an address, but normally addresses
-  are displayed in hex.  To have a numeric field displayed as a hex
-  value, simply append '.hex' to the field name in the trigger:
-
-    # echo 'hist:key=call_site.hex:val=bytes_req' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.hex:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-    { call_site: ffffffffa026b291 } hitcount:          1  bytes_req:        433
-    { call_site: ffffffffa07186ff } hitcount:          1  bytes_req:        176
-    { call_site: ffffffff811ae721 } hitcount:          1  bytes_req:      16384
-    { call_site: ffffffff811c5134 } hitcount:          1  bytes_req:          8
-    { call_site: ffffffffa04a9ebb } hitcount:          1  bytes_req:        511
-    { call_site: ffffffff8122e0a6 } hitcount:          1  bytes_req:         12
-    { call_site: ffffffff8107da84 } hitcount:          1  bytes_req:        152
-    { call_site: ffffffff812d8246 } hitcount:          1  bytes_req:         24
-    { call_site: ffffffff811dc1e5 } hitcount:          3  bytes_req:        144
-    { call_site: ffffffffa02515e8 } hitcount:          3  bytes_req:        648
-    { call_site: ffffffff81258159 } hitcount:          3  bytes_req:        144
-    { call_site: ffffffff811c80f4 } hitcount:          4  bytes_req:        544
-    .
-    .
-    .
-    { call_site: ffffffffa06c7646 } hitcount:        106  bytes_req:       8024
-    { call_site: ffffffffa06cb246 } hitcount:        132  bytes_req:      31680
-    { call_site: ffffffffa06cef7a } hitcount:        132  bytes_req:       2112
-    { call_site: ffffffff8137e399 } hitcount:        132  bytes_req:      23232
-    { call_site: ffffffffa06c941c } hitcount:        185  bytes_req:     171360
-    { call_site: ffffffffa06f2a66 } hitcount:        185  bytes_req:      26640
-    { call_site: ffffffffa036a70e } hitcount:        265  bytes_req:      10600
-    { call_site: ffffffff81325447 } hitcount:        292  bytes_req:        584
-    { call_site: ffffffffa072da3c } hitcount:        446  bytes_req:      60656
-    { call_site: ffffffffa036b1f2 } hitcount:        526  bytes_req:      29456
-    { call_site: ffffffffa0099c06 } hitcount:       1780  bytes_req:      35600
-
-    Totals:
-        Hits: 4775
-        Entries: 46
-        Dropped: 0
-
-  Even that's only marginally more useful - while hex values do look
-  more like addresses, what users are typically more interested in
-  when looking at text addresses are the corresponding symbols
-  instead.  To have an address displayed as symbolic value instead,
-  simply append '.sym' or '.sym-offset' to the field name in the
-  trigger:
-
-    # echo 'hist:key=call_site.sym:val=bytes_req' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-    { call_site: [ffffffff810adcb9] syslog_print_all                              } hitcount:          1  bytes_req:       1024
-    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffff8154acbe] usb_alloc_urb                                 } hitcount:          1  bytes_req:        192
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
-    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff811febd5] fsnotify_alloc_group                          } hitcount:          2  bytes_req:        528
-    { call_site: [ffffffff81440f58] __tty_buffer_request_room                     } hitcount:          2  bytes_req:       2624
-    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          2  bytes_req:         96
-    { call_site: [ffffffffa05e19af] ieee80211_start_tx_ba_session [mac80211]      } hitcount:          2  bytes_req:        464
-    { call_site: [ffffffff81672406] tcp_get_metrics                               } hitcount:          2  bytes_req:        304
-    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff81089b05] sched_create_group                            } hitcount:          2  bytes_req:       1424
-    .
-    .
-    .
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1185  bytes_req:     123240
-    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:       1185  bytes_req:     104280
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       1402  bytes_req:     190672
-    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       1518  bytes_req:     146208
-    { call_site: [ffffffffa029070e] drm_vma_node_allow [drm]                      } hitcount:       1746  bytes_req:      69840
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       2021  bytes_req:     792312
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       2592  bytes_req:     145152
-    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2629  bytes_req:     378576
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2629  bytes_req:    3783248
-    { call_site: [ffffffff81325607] apparmor_file_alloc_security                  } hitcount:       5192  bytes_req:      10384
-    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       5529  bytes_req:     110584
-    { call_site: [ffffffff8131ebf7] aa_alloc_task_context                         } hitcount:      21943  bytes_req:     702176
-    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:      55759  bytes_req:    5074265
-
-    Totals:
-        Hits: 109928
-        Entries: 71
-        Dropped: 0
-
-  Because the default sort key above is 'hitcount', the above shows a
-  the list of call_sites by increasing hitcount, so that at the bottom
-  we see the functions that made the most kmalloc calls during the
-  run.  If instead we we wanted to see the top kmalloc callers in
-  terms of the number of bytes requested rather than the number of
-  calls, and we wanted the top caller to appear at the top, we can use
-  the 'sort' parameter, along with the 'descending' modifier:
-
-    # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
-
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2186  bytes_req:    3397464
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1790  bytes_req:     712176
-    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       8132  bytes_req:     513135
-    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        106  bytes_req:     440128
-    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2186  bytes_req:     314784
-    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       2174  bytes_req:     208992
-    { call_site: [ffffffff811ae8e1] __kmalloc                                     } hitcount:          8  bytes_req:     131072
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:        859  bytes_req:     116824
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       1834  bytes_req:     102704
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:        972  bytes_req:     101088
-    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:        972  bytes_req:      85536
-    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       3333  bytes_req:      66664
-    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        209  bytes_req:      61632
-    .
-    .
-    .
-    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff812d8406] copy_semundo                                  } hitcount:          2  bytes_req:         48
-    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          1  bytes_req:         48
-    { call_site: [ffffffffa027121a] drm_getmagic [drm]                            } hitcount:          1  bytes_req:         48
-    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
-    { call_site: [ffffffff811c52f4] bprm_change_interp                            } hitcount:          2  bytes_req:         16
-    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
-
-    Totals:
-        Hits: 32133
-        Entries: 81
-        Dropped: 0
-
-  To display the offset and size information in addition to the symbol
-  name, just use 'sym-offset' instead:
-
-    # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym-offset:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
-
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2+0x6c/0x2c0 [i915]                  } hitcount:       4569  bytes_req:    3163720
-    { call_site: [ffffffffa0489a66] intel_ring_begin+0xc6/0x1f0 [i915]                      } hitcount:       4569  bytes_req:     657936
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23+0x694/0x1020 [i915]      } hitcount:       1519  bytes_req:     472936
-    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23+0x516/0x1020 [i915]      } hitcount:       3050  bytes_req:     211832
-    { call_site: [ffffffff811e2a1b] seq_buf_alloc+0x1b/0x50                                 } hitcount:         34  bytes_req:     148384
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip+0xbc/0x870 [i915]                  } hitcount:       1385  bytes_req:     144040
-    { call_site: [ffffffff811ae8e1] __kmalloc+0x191/0x1b0                                   } hitcount:          8  bytes_req:     131072
-    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl+0x282/0x360 [drm]              } hitcount:       1385  bytes_req:     121880
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc+0x32/0x100 [drm]                  } hitcount:       1848  bytes_req:     103488
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state+0x2c/0xa0 [i915]            } hitcount:        461  bytes_req:      62696
-    { call_site: [ffffffffa029070e] drm_vma_node_allow+0x2e/0xd0 [drm]                      } hitcount:       1541  bytes_req:      61640
-    { call_site: [ffffffff815f8d7b] sk_prot_alloc+0xcb/0x1b0                                } hitcount:         57  bytes_req:      57456
-    .
-    .
-    .
-    { call_site: [ffffffff8109524a] alloc_fair_sched_group+0x5a/0x1a0                       } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffffa027b921] drm_vm_open_locked+0x31/0xa0 [drm]                      } hitcount:          3  bytes_req:         96
-    { call_site: [ffffffff8122e266] proc_self_follow_link+0x76/0xb0                         } hitcount:          8  bytes_req:         96
-    { call_site: [ffffffff81213e80] load_elf_binary+0x240/0x1650                            } hitcount:          3  bytes_req:         84
-    { call_site: [ffffffff8154bc62] usb_control_msg+0x42/0x110                              } hitcount:          1  bytes_req:          8
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report+0x7e/0x1a0 [hid]                     } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event+0x8a/0x120 [hid]                    } hitcount:          1  bytes_req:          7
-
-    Totals:
-        Hits: 26098
-        Entries: 64
-        Dropped: 0
-
-  We can also add multiple fields to the 'values' parameter.  For
-  example, we might want to see the total number of bytes allocated
-  alongside bytes requested, and display the result sorted by bytes
-  allocated in a descending order:
-
-    # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym:vals=bytes_req,bytes_alloc:sort=bytes_alloc.descending:size=2048 [active]
-
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       7403  bytes_req:    4084360  bytes_alloc:    5958016
-    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        541  bytes_req:    2213968  bytes_alloc:    2228224
-    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       7404  bytes_req:    1066176  bytes_alloc:    1421568
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1565  bytes_req:     557368  bytes_alloc:    1037760
-    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       9557  bytes_req:     595778  bytes_alloc:     695744
-    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       5839  bytes_req:     430680  bytes_alloc:     470400
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       2388  bytes_req:     324768  bytes_alloc:     458496
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       3911  bytes_req:     219016  bytes_alloc:     250304
-    { call_site: [ffffffff815f8d7b] sk_prot_alloc                                 } hitcount:        235  bytes_req:     236880  bytes_alloc:     240640
-    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        557  bytes_req:     169024  bytes_alloc:     221760
-    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       9378  bytes_req:     187548  bytes_alloc:     206312
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1519  bytes_req:     157976  bytes_alloc:     194432
-    .
-    .
-    .
-    { call_site: [ffffffff8109bd3b] sched_autogroup_create_attach                 } hitcount:          2  bytes_req:        144  bytes_alloc:        192
-    { call_site: [ffffffff81097ee8] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff81213e80] load_elf_binary                               } hitcount:          3  bytes_req:         84  bytes_alloc:         96
-    { call_site: [ffffffff81079a2e] kthread_create_on_node                        } hitcount:          1  bytes_req:         56  bytes_alloc:         64
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7  bytes_alloc:          8
-    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8  bytes_alloc:          8
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7  bytes_alloc:          8
-
-    Totals:
-        Hits: 66598
-        Entries: 65
-        Dropped: 0
-
-  Finally, to finish off our kmalloc example, instead of simply having
-  the hist trigger display symbolic call_sites, we can have the hist
-  trigger additionally display the complete set of kernel stack traces
-  that led to each call_site.  To do that, we simply use the special
-  value 'stacktrace' for the key parameter:
-
-    # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-  The above trigger will use the kernel stack trace in effect when an
-  event is triggered as the key for the hash table.  This allows the
-  enumeration of every kernel callpath that led up to a particular
-  event, along with a running total of any of the event fields for
-  that event.  Here we tally bytes requested and bytes allocated for
-  every callpath in the system that led up to a kmalloc (in this case
-  every callpath to a kmalloc for a kernel compile):
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
-
-    { stacktrace:
-         __kmalloc_track_caller+0x10b/0x1a0
-         kmemdup+0x20/0x50
-         hidraw_report_event+0x8a/0x120 [hid]
-         hid_report_raw_event+0x3ea/0x440 [hid]
-         hid_input_report+0x112/0x190 [hid]
-         hid_irq_in+0xc2/0x260 [usbhid]
-         __usb_hcd_giveback_urb+0x72/0x120
-         usb_giveback_urb_bh+0x9e/0xe0
-         tasklet_hi_action+0xf8/0x100
-         __do_softirq+0x114/0x2c0
-         irq_exit+0xa5/0xb0
-         do_IRQ+0x5a/0xf0
-         ret_from_intr+0x0/0x30
-         cpuidle_enter+0x17/0x20
-         cpu_startup_entry+0x315/0x3e0
-         rest_init+0x7c/0x80
-    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
-    { stacktrace:
-         __kmalloc_track_caller+0x10b/0x1a0
-         kmemdup+0x20/0x50
-         hidraw_report_event+0x8a/0x120 [hid]
-         hid_report_raw_event+0x3ea/0x440 [hid]
-         hid_input_report+0x112/0x190 [hid]
-         hid_irq_in+0xc2/0x260 [usbhid]
-         __usb_hcd_giveback_urb+0x72/0x120
-         usb_giveback_urb_bh+0x9e/0xe0
-         tasklet_hi_action+0xf8/0x100
-         __do_softirq+0x114/0x2c0
-         irq_exit+0xa5/0xb0
-         do_IRQ+0x5a/0xf0
-         ret_from_intr+0x0/0x30
-    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
-    { stacktrace:
-         kmem_cache_alloc_trace+0xeb/0x150
-         aa_alloc_task_context+0x27/0x40
-         apparmor_cred_prepare+0x1f/0x50
-         security_prepare_creds+0x16/0x20
-         prepare_creds+0xdf/0x1a0
-         SyS_capset+0xb5/0x200
-         system_call_fastpath+0x12/0x6a
-    } hitcount:          1  bytes_req:         32  bytes_alloc:         32
-    .
-    .
-    .
-    { stacktrace:
-         __kmalloc+0x11b/0x1b0
-         i915_gem_execbuffer2+0x6c/0x2c0 [i915]
-         drm_ioctl+0x349/0x670 [drm]
-         do_vfs_ioctl+0x2f0/0x4f0
-         SyS_ioctl+0x81/0xa0
-         system_call_fastpath+0x12/0x6a
-    } hitcount:      17726  bytes_req:   13944120  bytes_alloc:   19593808
-    { stacktrace:
-         __kmalloc+0x11b/0x1b0
-         load_elf_phdrs+0x76/0xa0
-         load_elf_binary+0x102/0x1650
-         search_binary_handler+0x97/0x1d0
-         do_execveat_common.isra.34+0x551/0x6e0
-         SyS_execve+0x3a/0x50
-         return_from_execve+0x0/0x23
-    } hitcount:      33348  bytes_req:   17152128  bytes_alloc:   20226048
-    { stacktrace:
-         kmem_cache_alloc_trace+0xeb/0x150
-         apparmor_file_alloc_security+0x27/0x40
-         security_file_alloc+0x16/0x20
-         get_empty_filp+0x93/0x1c0
-         path_openat+0x31/0x5f0
-         do_filp_open+0x3a/0x90
-         do_sys_open+0x128/0x220
-         SyS_open+0x1e/0x20
-         system_call_fastpath+0x12/0x6a
-    } hitcount:    4766422  bytes_req:    9532844  bytes_alloc:   38131376
-    { stacktrace:
-         __kmalloc+0x11b/0x1b0
-         seq_buf_alloc+0x1b/0x50
-         seq_read+0x2cc/0x370
-         proc_reg_read+0x3d/0x80
-         __vfs_read+0x28/0xe0
-         vfs_read+0x86/0x140
-         SyS_read+0x46/0xb0
-         system_call_fastpath+0x12/0x6a
-    } hitcount:      19133  bytes_req:   78368768  bytes_alloc:   78368768
-
-    Totals:
-        Hits: 6085872
-        Entries: 253
-        Dropped: 0
-
-  If you key a hist trigger on common_pid, in order for example to
-  gather and display sorted totals for each process, you can use the
-  special .execname modifier to display the executable names for the
-  processes in the table rather than raw pids.  The example below
-  keeps a per-process sum of total bytes read:
-
-    # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
-           /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
-
-    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/hist
-    # trigger info: hist:keys=common_pid.execname:vals=count:sort=count.descending:size=2048 [active]
-
-    { common_pid: gnome-terminal  [      3196] } hitcount:        280  count:    1093512
-    { common_pid: Xorg            [      1309] } hitcount:        525  count:     256640
-    { common_pid: compiz          [      2889] } hitcount:         59  count:     254400
-    { common_pid: bash            [      8710] } hitcount:          3  count:      66369
-    { common_pid: dbus-daemon-lau [      8703] } hitcount:         49  count:      47739
-    { common_pid: irqbalance      [      1252] } hitcount:         27  count:      27648
-    { common_pid: 01ifupdown      [      8705] } hitcount:          3  count:      17216
-    { common_pid: dbus-daemon     [       772] } hitcount:         10  count:      12396
-    { common_pid: Socket Thread   [      8342] } hitcount:         11  count:      11264
-    { common_pid: nm-dhcp-client. [      8701] } hitcount:          6  count:       7424
-    { common_pid: gmain           [      1315] } hitcount:         18  count:       6336
-    .
-    .
-    .
-    { common_pid: postgres        [      1892] } hitcount:          2  count:         32
-    { common_pid: postgres        [      1891] } hitcount:          2  count:         32
-    { common_pid: gmain           [      8704] } hitcount:          2  count:         32
-    { common_pid: upstart-dbus-br [      2740] } hitcount:         21  count:         21
-    { common_pid: nm-dispatcher.a [      8696] } hitcount:          1  count:         16
-    { common_pid: indicator-datet [      2904] } hitcount:          1  count:         16
-    { common_pid: gdbus           [      2998] } hitcount:          1  count:         16
-    { common_pid: rtkit-daemon    [      2052] } hitcount:          1  count:          8
-    { common_pid: init            [         1] } hitcount:          2  count:          2
-
-    Totals:
-        Hits: 2116
-        Entries: 51
-        Dropped: 0
-
-  Similarly, if you key a hist trigger on syscall id, for example to
-  gather and display a list of systemwide syscall hits, you can use
-  the special .syscall modifier to display the syscall names rather
-  than raw ids.  The example below keeps a running total of syscall
-  counts for the system during the run:
-
-    # echo 'hist:key=id.syscall:val=hitcount' > \
-           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
-    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
-    # trigger info: hist:keys=id.syscall:vals=hitcount:sort=hitcount:size=2048 [active]
-
-    { id: sys_fsync                     [ 74] } hitcount:          1
-    { id: sys_newuname                  [ 63] } hitcount:          1
-    { id: sys_prctl                     [157] } hitcount:          1
-    { id: sys_statfs                    [137] } hitcount:          1
-    { id: sys_symlink                   [ 88] } hitcount:          1
-    { id: sys_sendmmsg                  [307] } hitcount:          1
-    { id: sys_semctl                    [ 66] } hitcount:          1
-    { id: sys_readlink                  [ 89] } hitcount:          3
-    { id: sys_bind                      [ 49] } hitcount:          3
-    { id: sys_getsockname               [ 51] } hitcount:          3
-    { id: sys_unlink                    [ 87] } hitcount:          3
-    { id: sys_rename                    [ 82] } hitcount:          4
-    { id: unknown_syscall               [ 58] } hitcount:          4
-    { id: sys_connect                   [ 42] } hitcount:          4
-    { id: sys_getpid                    [ 39] } hitcount:          4
-    .
-    .
-    .
-    { id: sys_rt_sigprocmask            [ 14] } hitcount:        952
-    { id: sys_futex                     [202] } hitcount:       1534
-    { id: sys_write                     [  1] } hitcount:       2689
-    { id: sys_setitimer                 [ 38] } hitcount:       2797
-    { id: sys_read                      [  0] } hitcount:       3202
-    { id: sys_select                    [ 23] } hitcount:       3773
-    { id: sys_writev                    [ 20] } hitcount:       4531
-    { id: sys_poll                      [  7] } hitcount:       8314
-    { id: sys_recvmsg                   [ 47] } hitcount:      13738
-    { id: sys_ioctl                     [ 16] } hitcount:      21843
-
-    Totals:
-        Hits: 67612
-        Entries: 72
-        Dropped: 0
-
-    The syscall counts above provide a rough overall picture of system
-    call activity on the system; we can see for example that the most
-    popular system call on this system was the 'sys_ioctl' system call.
-
-    We can use 'compound' keys to refine that number and provide some
-    further insight as to which processes exactly contribute to the
-    overall ioctl count.
-
-    The command below keeps a hitcount for every unique combination of
-    system call id and pid - the end result is essentially a table
-    that keeps a per-pid sum of system call hits.  The results are
-    sorted using the system call id as the primary key, and the
-    hitcount sum as the secondary key:
-
-    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
-           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
-    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
-    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 [active]
-
-    { id: sys_read                      [  0], common_pid: rtkit-daemon    [      1877] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: gdbus           [      2976] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: console-kit-dae [      3400] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: postgres        [      1865] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: deja-dup-monito [      3543] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: NetworkManager  [       890] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: evolution-calen [      3048] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: postgres        [      1864] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: nm-applet       [      3022] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: whoopsie        [      1212] } hitcount:          2
-    .
-    .
-    .
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      8479] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      3472] } hitcount:         12
-    { id: sys_ioctl                     [ 16], common_pid: gnome-terminal  [      3199] } hitcount:         16
-    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:       1808
-    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:       5580
-    .
-    .
-    .
-    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2690] } hitcount:          3
-    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2688] } hitcount:         16
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [       975] } hitcount:          2
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3204] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2888] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3003] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2873] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3196] } hitcount:          6
-    { id: sys_openat                    [257], common_pid: java            [      2623] } hitcount:          2
-    { id: sys_eventfd2                  [290], common_pid: ibus-ui-gtk3    [      2760] } hitcount:          4
-    { id: sys_eventfd2                  [290], common_pid: compiz          [      2994] } hitcount:          6
-
-    Totals:
-        Hits: 31536
-        Entries: 323
-        Dropped: 0
-
-    The above list does give us a breakdown of the ioctl syscall by
-    pid, but it also gives us quite a bit more than that, which we
-    don't really care about at the moment.  Since we know the syscall
-    id for sys_ioctl (16, displayed next to the sys_ioctl name), we
-    can use that to filter out all the other syscalls:
-
-    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
-           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
-    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
-    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 if id == 16 [active]
-
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2769] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: evolution-addre [      8571] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      3003] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2781] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2829] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      8726] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      8508] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2970] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2768] } hitcount:          1
-    .
-    .
-    .
-    { id: sys_ioctl                     [ 16], common_pid: pool            [      8559] } hitcount:         45
-    { id: sys_ioctl                     [ 16], common_pid: pool            [      8555] } hitcount:         48
-    { id: sys_ioctl                     [ 16], common_pid: pool            [      8551] } hitcount:         48
-    { id: sys_ioctl                     [ 16], common_pid: avahi-daemon    [       896] } hitcount:         66
-    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:      26674
-    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:      73443
-
-    Totals:
-        Hits: 101162
-        Entries: 103
-        Dropped: 0
-
-    The above output shows that 'compiz' and 'Xorg' are far and away
-    the heaviest ioctl callers (which might lead to questions about
-    whether they really need to be making all those calls and to
-    possible avenues for further investigation.)
-
-    The compound key examples used a key and a sum value (hitcount) to
-    sort the output, but we can just as easily use two keys instead.
-    Here's an example where we use a compound key composed of the the
-    common_pid and size event fields.  Sorting with pid as the primary
-    key and 'size' as the secondary key allows us to display an
-    ordered summary of the recvfrom sizes, with counts, received by
-    each process:
-
-    # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
-           /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
-
-    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/hist
-    # trigger info: hist:keys=common_pid.execname,size:vals=hitcount:sort=common_pid.execname,size:size=2048 [active]
-
-    { common_pid: smbd            [       784], size:          4 } hitcount:          1
-    { common_pid: dnsmasq         [      1412], size:       4096 } hitcount:        672
-    { common_pid: postgres        [      1796], size:       1000 } hitcount:          6
-    { common_pid: postgres        [      1867], size:       1000 } hitcount:         10
-    { common_pid: bamfdaemon      [      2787], size:         28 } hitcount:          2
-    { common_pid: bamfdaemon      [      2787], size:      14360 } hitcount:          1
-    { common_pid: compiz          [      2994], size:          8 } hitcount:          1
-    { common_pid: compiz          [      2994], size:         20 } hitcount:         11
-    { common_pid: gnome-terminal  [      3199], size:          4 } hitcount:          2
-    { common_pid: firefox         [      8817], size:          4 } hitcount:          1
-    { common_pid: firefox         [      8817], size:          8 } hitcount:          5
-    { common_pid: firefox         [      8817], size:        588 } hitcount:          2
-    { common_pid: firefox         [      8817], size:        628 } hitcount:          1
-    { common_pid: firefox         [      8817], size:       6944 } hitcount:          1
-    { common_pid: firefox         [      8817], size:     408880 } hitcount:          2
-    { common_pid: firefox         [      8822], size:          8 } hitcount:          2
-    { common_pid: firefox         [      8822], size:        160 } hitcount:          2
-    { common_pid: firefox         [      8822], size:        320 } hitcount:          2
-    { common_pid: firefox         [      8822], size:        352 } hitcount:          1
-    .
-    .
-    .
-    { common_pid: pool            [      8923], size:       1960 } hitcount:         10
-    { common_pid: pool            [      8923], size:       2048 } hitcount:         10
-    { common_pid: pool            [      8924], size:       1960 } hitcount:         10
-    { common_pid: pool            [      8924], size:       2048 } hitcount:         10
-    { common_pid: pool            [      8928], size:       1964 } hitcount:          4
-    { common_pid: pool            [      8928], size:       1965 } hitcount:          2
-    { common_pid: pool            [      8928], size:       2048 } hitcount:          6
-    { common_pid: pool            [      8929], size:       1982 } hitcount:          1
-    { common_pid: pool            [      8929], size:       2048 } hitcount:          1
-
-    Totals:
-        Hits: 2016
-        Entries: 224
-        Dropped: 0
-
-  The above example also illustrates the fact that although a compound
-  key is treated as a single entity for hashing purposes, the sub-keys
-  it's composed of can be accessed independently.
-
-  The next example uses a string field as the hash key and
-  demonstrates how you can manually pause and continue a hist trigger.
-  In this example, we'll aggregate fork counts and don't expect a
-  large number of entries in the hash table, so we'll drop it to a
-  much smaller number, say 256:
-
-    # echo 'hist:key=child_comm:val=hitcount:size=256' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
-
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: ibus-daemon                         } hitcount:          1
-    { child_comm: whoopsie                            } hitcount:          1
-    { child_comm: smbd                                } hitcount:          1
-    { child_comm: gdbus                               } hitcount:          1
-    { child_comm: kthreadd                            } hitcount:          1
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: evolution-alarm                     } hitcount:          2
-    { child_comm: Socket Thread                       } hitcount:          2
-    { child_comm: postgres                            } hitcount:          2
-    { child_comm: bash                                } hitcount:          3
-    { child_comm: compiz                              } hitcount:          3
-    { child_comm: evolution-sourc                     } hitcount:          4
-    { child_comm: dhclient                            } hitcount:          4
-    { child_comm: pool                                } hitcount:          5
-    { child_comm: nm-dispatcher.a                     } hitcount:          8
-    { child_comm: firefox                             } hitcount:          8
-    { child_comm: dbus-daemon                         } hitcount:          8
-    { child_comm: glib-pacrunner                      } hitcount:         10
-    { child_comm: evolution                           } hitcount:         23
-
-    Totals:
-        Hits: 89
-        Entries: 20
-        Dropped: 0
-
-  If we want to pause the hist trigger, we can simply append :pause to
-  the command that started the trigger.  Notice that the trigger info
-  displays as [paused]:
-
-    # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [paused]
-
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: kthreadd                            } hitcount:          1
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: gdbus                               } hitcount:          1
-    { child_comm: ibus-daemon                         } hitcount:          1
-    { child_comm: Socket Thread                       } hitcount:          2
-    { child_comm: evolution-alarm                     } hitcount:          2
-    { child_comm: smbd                                } hitcount:          2
-    { child_comm: bash                                } hitcount:          3
-    { child_comm: whoopsie                            } hitcount:          3
-    { child_comm: compiz                              } hitcount:          3
-    { child_comm: evolution-sourc                     } hitcount:          4
-    { child_comm: pool                                } hitcount:          5
-    { child_comm: postgres                            } hitcount:          6
-    { child_comm: firefox                             } hitcount:          8
-    { child_comm: dhclient                            } hitcount:         10
-    { child_comm: emacs                               } hitcount:         12
-    { child_comm: dbus-daemon                         } hitcount:         20
-    { child_comm: nm-dispatcher.a                     } hitcount:         20
-    { child_comm: evolution                           } hitcount:         35
-    { child_comm: glib-pacrunner                      } hitcount:         59
-
-    Totals:
-        Hits: 199
-        Entries: 21
-        Dropped: 0
-
-  To manually continue having the trigger aggregate events, append
-  :cont instead.  Notice that the trigger info displays as [active]
-  again, and the data has changed:
-
-    # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
-
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: kthreadd                            } hitcount:          1
-    { child_comm: gdbus                               } hitcount:          1
-    { child_comm: ibus-daemon                         } hitcount:          1
-    { child_comm: Socket Thread                       } hitcount:          2
-    { child_comm: evolution-alarm                     } hitcount:          2
-    { child_comm: smbd                                } hitcount:          2
-    { child_comm: whoopsie                            } hitcount:          3
-    { child_comm: compiz                              } hitcount:          3
-    { child_comm: evolution-sourc                     } hitcount:          4
-    { child_comm: bash                                } hitcount:          5
-    { child_comm: pool                                } hitcount:          5
-    { child_comm: postgres                            } hitcount:          6
-    { child_comm: firefox                             } hitcount:          8
-    { child_comm: dhclient                            } hitcount:         11
-    { child_comm: emacs                               } hitcount:         12
-    { child_comm: dbus-daemon                         } hitcount:         22
-    { child_comm: nm-dispatcher.a                     } hitcount:         22
-    { child_comm: evolution                           } hitcount:         35
-    { child_comm: glib-pacrunner                      } hitcount:         59
-
-    Totals:
-        Hits: 206
-        Entries: 21
-        Dropped: 0
-
-  The previous example showed how to start and stop a hist trigger by
-  appending 'pause' and 'continue' to the hist trigger command.  A
-  hist trigger can also be started in a paused state by initially
-  starting the trigger with ':pause' appended.  This allows you to
-  start the trigger only when you're ready to start collecting data
-  and not before.  For example, you could start the trigger in a
-  paused state, then unpause it and do something you want to measure,
-  then pause the trigger again when done.
-
-  Of course, doing this manually can be difficult and error-prone, but
-  it is possible to automatically start and stop a hist trigger based
-  on some condition, via the enable_hist and disable_hist triggers.
-
-  For example, suppose we wanted to take a look at the relative
-  weights in terms of skb length for each callpath that leads to a
-  netif_receieve_skb event when downloading a decent-sized file using
-  wget.
-
-  First we set up an initially paused stacktrace trigger on the
-  netif_receive_skb event:
-
-    # echo 'hist:key=stacktrace:vals=len:pause' > \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  Next, we set up an 'enable_hist' trigger on the sched_process_exec
-  event, with an 'if filename==/usr/bin/wget' filter.  The effect of
-  this new trigger is that it will 'unpause' the hist trigger we just
-  set up on netif_receive_skb if and only if it sees a
-  sched_process_exec event with a filename of '/usr/bin/wget'.  When
-  that happens, all netif_receive_skb events are aggregated into a
-  hash table keyed on stacktrace:
-
-    # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
-  The aggregation continues until the netif_receive_skb is paused
-  again, which is what the following disable_hist event does by
-  creating a similar setup on the sched_process_exit event, using the
-  filter 'comm==wget':
-
-    # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
-  Whenever a process exits and the comm field of the disable_hist
-  trigger filter matches 'comm==wget', the netif_receive_skb hist
-  trigger is disabled.
-
-  The overall effect is that netif_receive_skb events are aggregated
-  into the hash table for only the duration of the wget.  Executing a
-  wget command and then listing the 'hist' file will display the
-  output generated by the wget command:
-
-    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
-
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         netif_receive_skb_internal+0x23/0x90
-         napi_gro_receive+0xc8/0x100
-         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
-         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
-         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
-         ieee80211_rx+0x31d/0x900 [mac80211]
-         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
-         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
-         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
-         irq_thread_fn+0x20/0x50
-         irq_thread+0x11f/0x150
-         kthread+0xd2/0xf0
-         ret_from_fork+0x42/0x70
-    } hitcount:         85  len:      28884
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         netif_receive_skb_internal+0x23/0x90
-         napi_gro_complete+0xa4/0xe0
-         dev_gro_receive+0x23a/0x360
-         napi_gro_receive+0x30/0x100
-         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
-         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
-         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
-         ieee80211_rx+0x31d/0x900 [mac80211]
-         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
-         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
-         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
-         irq_thread_fn+0x20/0x50
-         irq_thread+0x11f/0x150
-         kthread+0xd2/0xf0
-    } hitcount:         98  len:     664329
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         process_backlog+0xa8/0x150
-         net_rx_action+0x15d/0x340
-         __do_softirq+0x114/0x2c0
-         do_softirq_own_stack+0x1c/0x30
-         do_softirq+0x65/0x70
-         __local_bh_enable_ip+0xb5/0xc0
-         ip_finish_output+0x1f4/0x840
-         ip_output+0x6b/0xc0
-         ip_local_out_sk+0x31/0x40
-         ip_send_skb+0x1a/0x50
-         udp_send_skb+0x173/0x2a0
-         udp_sendmsg+0x2bf/0x9f0
-         inet_sendmsg+0x64/0xa0
-         sock_sendmsg+0x3d/0x50
-    } hitcount:        115  len:      13030
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         netif_receive_skb_internal+0x23/0x90
-         napi_gro_complete+0xa4/0xe0
-         napi_gro_flush+0x6d/0x90
-         iwl_pcie_irq_handler+0x92a/0x12f0 [iwlwifi]
-         irq_thread_fn+0x20/0x50
-         irq_thread+0x11f/0x150
-         kthread+0xd2/0xf0
-         ret_from_fork+0x42/0x70
-    } hitcount:        934  len:    5512212
-
-    Totals:
-        Hits: 1232
-        Entries: 4
-        Dropped: 0
-
-  The above shows all the netif_receive_skb callpaths and their total
-  lengths for the duration of the wget command.
-
-  The 'clear' hist trigger param can be used to clear the hash table.
-  Suppose we wanted to try another run of the previous example but
-  this time also wanted to see the complete list of events that went
-  into the histogram.  In order to avoid having to set everything up
-  again, we can just clear the histogram first:
-
-    # echo 'hist:key=stacktrace:vals=len:clear' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  Just to verify that it is in fact cleared, here's what we now see in
-  the hist file:
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
-
-    Totals:
-        Hits: 0
-        Entries: 0
-        Dropped: 0
-
-  Since we want to see the detailed list of every netif_receive_skb
-  event occurring during the new run, which are in fact the same
-  events being aggregated into the hash table, we add some additional
-  'enable_event' events to the triggering sched_process_exec and
-  sched_process_exit events as such:
-
-    # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
-    # echo 'disable_event:net:netif_receive_skb if comm==wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
-  If you read the trigger files for the sched_process_exec and
-  sched_process_exit triggers, you should see two triggers for each:
-  one enabling/disabling the hist aggregation and the other
-  enabling/disabling the logging of events:
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-    enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
-    enable_hist:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-    enable_event:net:netif_receive_skb:unlimited if comm==wget
-    disable_hist:net:netif_receive_skb:unlimited if comm==wget
-
-  In other words, whenever either of the sched_process_exec or
-  sched_process_exit events is hit and matches 'wget', it enables or
-  disables both the histogram and the event log, and what you end up
-  with is a hash table and set of events just covering the specified
-  duration.  Run the wget command again:
-
-    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
-
-  Displaying the 'hist' file should show something similar to what you
-  saw in the last run, but this time you should also see the
-  individual events in the trace file:
-
-    # cat /sys/kernel/debug/tracing/trace
-
-    # tracer: nop
-    #
-    # entries-in-buffer/entries-written: 183/1426   #P:4
-    #
-    #                              _-----=> irqs-off
-    #                             / _----=> need-resched
-    #                            | / _---=> hardirq/softirq
-    #                            || / _--=> preempt-depth
-    #                            ||| /     delay
-    #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
-    #              | |       |   ||||       |         |
-                wget-15108 [000] ..s1 31769.606929: netif_receive_skb: dev=lo skbaddr=ffff88009c353100 len=60
-                wget-15108 [000] ..s1 31769.606999: netif_receive_skb: dev=lo skbaddr=ffff88009c353200 len=60
-             dnsmasq-1382  [000] ..s1 31769.677652: netif_receive_skb: dev=lo skbaddr=ffff88009c352b00 len=130
-             dnsmasq-1382  [000] ..s1 31769.685917: netif_receive_skb: dev=lo skbaddr=ffff88009c352200 len=138
-    ##### CPU 2 buffer started ####
-      irq/29-iwlwifi-559   [002] ..s. 31772.031529: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433d00 len=2948
-      irq/29-iwlwifi-559   [002] ..s. 31772.031572: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432200 len=1500
-      irq/29-iwlwifi-559   [002] ..s. 31772.032196: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433100 len=2948
-      irq/29-iwlwifi-559   [002] ..s. 31772.032761: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433000 len=2948
-      irq/29-iwlwifi-559   [002] ..s. 31772.033220: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432e00 len=1500
-    .
-    .
-    .
-
-  The following example demonstrates how multiple hist triggers can be
-  attached to a given event.  This capability can be useful for
-  creating a set of different summaries derived from the same set of
-  events, or for comparing the effects of different filters, among
-  other things.
-
-    # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=skbaddr.hex:vals=len if len > 4096' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=skbaddr.hex:vals=len if len == 256' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=skbaddr.hex:vals=len' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=len:vals=common_preempt_count' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  The above set of commands create four triggers differing only in
-  their filters, along with a completely different though fairly
-  nonsensical trigger.  Note that in order to append multiple hist
-  triggers to the same file, you should use the '>>' operator to
-  append them ('>' will also add the new hist trigger, but will remove
-  any existing hist triggers beforehand).
-
-  Displaying the contents of the 'hist' file for the event shows the
-  contents of all five histograms:
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-
-    # event histogram
-    #
-    # trigger info: hist:keys=len:vals=hitcount,common_preempt_count:sort=hitcount:size=2048 [active]
-    #
-
-    { len:        176 } hitcount:          1  common_preempt_count:          0
-    { len:        223 } hitcount:          1  common_preempt_count:          0
-    { len:       4854 } hitcount:          1  common_preempt_count:          0
-    { len:        395 } hitcount:          1  common_preempt_count:          0
-    { len:        177 } hitcount:          1  common_preempt_count:          0
-    { len:        446 } hitcount:          1  common_preempt_count:          0
-    { len:       1601 } hitcount:          1  common_preempt_count:          0
-    .
-    .
-    .
-    { len:       1280 } hitcount:         66  common_preempt_count:          0
-    { len:        116 } hitcount:         81  common_preempt_count:         40
-    { len:        708 } hitcount:        112  common_preempt_count:          0
-    { len:         46 } hitcount:        221  common_preempt_count:          0
-    { len:       1264 } hitcount:        458  common_preempt_count:          0
-
-    Totals:
-        Hits: 1428
-        Entries: 147
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
-    #
-
-    { skbaddr: ffff8800baee5e00 } hitcount:          1  len:        130
-    { skbaddr: ffff88005f3d5600 } hitcount:          1  len:       1280
-    { skbaddr: ffff88005f3d4900 } hitcount:          1  len:       1280
-    { skbaddr: ffff88009fed6300 } hitcount:          1  len:        115
-    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:        115
-    { skbaddr: ffff88008cdb1900 } hitcount:          1  len:         46
-    { skbaddr: ffff880064b5ef00 } hitcount:          1  len:        118
-    { skbaddr: ffff880044e3c700 } hitcount:          1  len:         60
-    { skbaddr: ffff880100065900 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d46bd500 } hitcount:          1  len:        116
-    { skbaddr: ffff88005f3d5f00 } hitcount:          1  len:       1280
-    { skbaddr: ffff880100064700 } hitcount:          1  len:        365
-    { skbaddr: ffff8800badb6f00 } hitcount:          1  len:         60
-    .
-    .
-    .
-    { skbaddr: ffff88009fe0be00 } hitcount:         27  len:      24677
-    { skbaddr: ffff88009fe0a400 } hitcount:         27  len:      23052
-    { skbaddr: ffff88009fe0b700 } hitcount:         31  len:      25589
-    { skbaddr: ffff88009fe0b600 } hitcount:         32  len:      27326
-    { skbaddr: ffff88006a462800 } hitcount:         68  len:      71678
-    { skbaddr: ffff88006a463700 } hitcount:         70  len:      72678
-    { skbaddr: ffff88006a462b00 } hitcount:         71  len:      77589
-    { skbaddr: ffff88006a463600 } hitcount:         73  len:      71307
-    { skbaddr: ffff88006a462200 } hitcount:         81  len:      81032
-
-    Totals:
-        Hits: 1451
-        Entries: 318
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len == 256 [active]
-    #
-
-
-    Totals:
-        Hits: 0
-        Entries: 0
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len > 4096 [active]
-    #
-
-    { skbaddr: ffff88009fd2c300 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcce00 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcd700 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcda00 } hitcount:          1  len:      21492
-    { skbaddr: ffff8800ae2e2d00 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcdb00 } hitcount:          1  len:       7212
-    { skbaddr: ffff88006a4df500 } hitcount:          1  len:       4854
-    { skbaddr: ffff88008ce47b00 } hitcount:          1  len:      18636
-    { skbaddr: ffff8800ae2e2200 } hitcount:          1  len:      12924
-    { skbaddr: ffff88005f3e1000 } hitcount:          1  len:       4356
-    { skbaddr: ffff8800d2bcdc00 } hitcount:          2  len:      24420
-    { skbaddr: ffff8800d2bcc200 } hitcount:          2  len:      12996
-
-    Totals:
-        Hits: 14
-        Entries: 12
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len < 0 [active]
-    #
-
-
-    Totals:
-        Hits: 0
-        Entries: 0
-        Dropped: 0
-
-  Named triggers can be used to have triggers share a common set of
-  histogram data.  This capability is mostly useful for combining the
-  output of events generated by tracepoints contained inside inline
-  functions, but names can be used in a hist trigger on any event.
-  For example, these two triggers when hit will update the same 'len'
-  field in the shared 'foo' histogram data:
-
-    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
-           /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  You can see that they're updating common histogram data by reading
-  each event's hist files at the same time:
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
-      cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
-    # event histogram
-    #
-    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
-    #
-
-    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
-    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
-    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
-    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
-    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
-    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
-    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
-    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
-    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
-    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
-    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
-    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
-    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
-    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
-    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
-    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
-    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
-    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
-    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
-    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
-    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
-    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
-    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
-    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
-    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
-    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
-    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
-    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
-    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
-    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
-    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
-    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
-    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
-    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
-    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
-    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
-    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
-
-    Totals:
-        Hits: 81
-        Entries: 42
-        Dropped: 0
-    # event histogram
-    #
-    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
-    #
-
-    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
-    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
-    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
-    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
-    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
-    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
-    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
-    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
-    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
-    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
-    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
-    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
-    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
-    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
-    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
-    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
-    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
-    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
-    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
-    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
-    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
-    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
-    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
-    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
-    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
-    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
-    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
-    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
-    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
-    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
-    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
-    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
-    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
-    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
-    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
-    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
-    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
-
-    Totals:
-        Hits: 81
-        Entries: 42
-        Dropped: 0
-
-  And here's an example that shows how to combine histogram data from
-  any two events even if they don't share any 'compatible' fields
-  other than 'hitcount' and 'stacktrace'.  These commands create a
-  couple of triggers named 'bar' using those fields:
-
-    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
-          /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  And displaying the output of either shows some interesting if
-  somewhat confusing output:
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
-    # event histogram
-    #
-    # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active]
-    #
-
-    { stacktrace:
-             _do_fork+0x18e/0x330
-             kernel_thread+0x29/0x30
-             kthreadd+0x154/0x1b0
-             ret_from_fork+0x3f/0x70
-    } hitcount:          1
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx_ni+0x20/0x70
-             dev_loopback_xmit+0xaa/0xd0
-             ip_mc_output+0x126/0x240
-             ip_local_out_sk+0x31/0x40
-             igmp_send_report+0x1e9/0x230
-             igmp_timer_expire+0xe9/0x120
-             call_timer_fn+0x39/0xf0
-             run_timer_softirq+0x1e1/0x290
-             __do_softirq+0xfd/0x290
-             irq_exit+0x98/0xb0
-             smp_apic_timer_interrupt+0x4a/0x60
-             apic_timer_interrupt+0x6d/0x80
-             cpuidle_enter+0x17/0x20
-             call_cpuidle+0x3b/0x60
-             cpu_startup_entry+0x22d/0x310
-    } hitcount:          1
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx_ni+0x20/0x70
-             dev_loopback_xmit+0xaa/0xd0
-             ip_mc_output+0x17f/0x240
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x13e/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             SYSC_sendto+0xef/0x170
-             SyS_sendto+0xe/0x10
-             entry_SYSCALL_64_fastpath+0x12/0x6a
-    } hitcount:          2
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx+0x1c/0x60
-             loopback_xmit+0x6c/0xb0
-             dev_hard_start_xmit+0x219/0x3a0
-             __dev_queue_xmit+0x415/0x4f0
-             dev_queue_xmit_sk+0x13/0x20
-             ip_finish_output2+0x237/0x340
-             ip_finish_output+0x113/0x1d0
-             ip_output+0x66/0xc0
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x16d/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             ___sys_sendmsg+0x14e/0x270
-    } hitcount:         76
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx+0x1c/0x60
-             loopback_xmit+0x6c/0xb0
-             dev_hard_start_xmit+0x219/0x3a0
-             __dev_queue_xmit+0x415/0x4f0
-             dev_queue_xmit_sk+0x13/0x20
-             ip_finish_output2+0x237/0x340
-             ip_finish_output+0x113/0x1d0
-             ip_output+0x66/0xc0
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x16d/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             ___sys_sendmsg+0x269/0x270
-    } hitcount:         77
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx+0x1c/0x60
-             loopback_xmit+0x6c/0xb0
-             dev_hard_start_xmit+0x219/0x3a0
-             __dev_queue_xmit+0x415/0x4f0
-             dev_queue_xmit_sk+0x13/0x20
-             ip_finish_output2+0x237/0x340
-             ip_finish_output+0x113/0x1d0
-             ip_output+0x66/0xc0
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x16d/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             SYSC_sendto+0xef/0x170
-    } hitcount:         88
-    { stacktrace:
-             _do_fork+0x18e/0x330
-             SyS_clone+0x19/0x20
-             entry_SYSCALL_64_fastpath+0x12/0x6a
-    } hitcount:        244
-
-    Totals:
-        Hits: 489
-        Entries: 7
-        Dropped: 0
+  See Documentation/trace/histogram.txt for details and examples.
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index d4601df6e72e..54213e5c23f6 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -539,6 +539,30 @@ of ftrace. Here is a list of some of the key files:
 
        See events.txt for more information.
 
+  timestamp_mode:
+
+       Certain tracers may change the timestamp mode used when
+       logging trace events into the event buffer.  Events with
+       different modes can coexist within a buffer but the mode in
+       effect when an event is logged determines which timestamp mode
+       is used for that event.  The default timestamp mode is
+       'delta'.
+
+       Usual timestamp modes for tracing:
+
+         # cat timestamp_mode
+         [delta] absolute
+
+         The timestamp mode with the square brackets around it is the
+         one in effect.
+
+         delta: Default timestamp mode - timestamp is a delta against
+                a per-buffer timestamp.
+
+         absolute: The timestamp is a full timestamp, not a delta
+                 against some other value.  As such it takes up more
+                 space and is less efficient.
+
   hwlat_detector:
 
        Directory for the Hardware Latency Detector.
diff --git a/Documentation/trace/histogram.txt b/Documentation/trace/histogram.txt
new file mode 100644
index 000000000000..6e05510afc28
--- /dev/null
+++ b/Documentation/trace/histogram.txt
@@ -0,0 +1,1995 @@
+                            Event Histograms
+
+                   Documentation written by Tom Zanussi
+
+1. Introduction
+===============
+
+  Histogram triggers are special event triggers that can be used to
+  aggregate trace event data into histograms.  For information on
+  trace events and event triggers, see Documentation/trace/events.txt.
+
+
+2. Histogram Trigger Command
+============================
+
+  A histogram trigger command is an event trigger command that
+  aggregates event hits into a hash table keyed on one or more trace
+  event format fields (or stacktrace) and a set of running totals
+  derived from one or more trace event format fields and/or event
+  counts (hitcount).
+
+  The format of a hist trigger is as follows:
+
+        hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
+          [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
+          [:clear][:name=histname1] [if <filter>]
+
+  When a matching event is hit, an entry is added to a hash table
+  using the key(s) and value(s) named.  Keys and values correspond to
+  fields in the event's format description.  Values must correspond to
+  numeric fields - on an event hit, the value(s) will be added to a
+  sum kept for that field.  The special string 'hitcount' can be used
+  in place of an explicit value field - this is simply a count of
+  event hits.  If 'values' isn't specified, an implicit 'hitcount'
+  value will be automatically created and used as the only value.
+  Keys can be any field, or the special string 'stacktrace', which
+  will use the event's kernel stacktrace as the key.  The keywords
+  'keys' or 'key' can be used to specify keys, and the keywords
+  'values', 'vals', or 'val' can be used to specify values.  Compound
+  keys consisting of up to two fields can be specified by the 'keys'
+  keyword.  Hashing a compound key produces a unique entry in the
+  table for each unique combination of component keys, and can be
+  useful for providing more fine-grained summaries of event data.
+  Additionally, sort keys consisting of up to two fields can be
+  specified by the 'sort' keyword.  If more than one field is
+  specified, the result will be a 'sort within a sort': the first key
+  is taken to be the primary sort key and the second the secondary
+  key.  If a hist trigger is given a name using the 'name' parameter,
+  its histogram data will be shared with other triggers of the same
+  name, and trigger hits will update this common data.  Only triggers
+  with 'compatible' fields can be combined in this way; triggers are
+  'compatible' if the fields named in the trigger share the same
+  number and type of fields and those fields also have the same names.
+  Note that any two events always share the compatible 'hitcount' and
+  'stacktrace' fields and can therefore be combined using those
+  fields, however pointless that may be.
+
+  'hist' triggers add a 'hist' file to each event's subdirectory.
+  Reading the 'hist' file for the event will dump the hash table in
+  its entirety to stdout.  If there are multiple hist triggers
+  attached to an event, there will be a table for each trigger in the
+  output.  The table displayed for a named trigger will be the same as
+  any other instance having the same name. Each printed hash table
+  entry is a simple list of the keys and values comprising the entry;
+  keys are printed first and are delineated by curly braces, and are
+  followed by the set of value fields for the entry.  By default,
+  numeric fields are displayed as base-10 integers.  This can be
+  modified by appending any of the following modifiers to the field
+  name:
+
+        .hex        display a number as a hex value
+       .sym        display an address as a symbol
+       .sym-offset display an address as a symbol and offset
+       .syscall    display a syscall id as a system call name
+       .execname   display a common_pid as a program name
+       .log2       display log2 value rather than raw number
+       .usecs      display a common_timestamp in microseconds
+
+  Note that in general the semantics of a given field aren't
+  interpreted when applying a modifier to it, but there are some
+  restrictions to be aware of in this regard:
+
+    - only the 'hex' modifier can be used for values (because values
+      are essentially sums, and the other modifiers don't make sense
+      in that context).
+    - the 'execname' modifier can only be used on a 'common_pid'.  The
+      reason for this is that the execname is simply the 'comm' value
+      saved for the 'current' process when an event was triggered,
+      which is the same as the common_pid value saved by the event
+      tracing code.  Trying to apply that comm value to other pid
+      values wouldn't be correct, and typically events that care save
+      pid-specific comm fields in the event itself.
+
+  A typical usage scenario would be the following to enable a hist
+  trigger, read its current contents, and then turn it off:
+
+  # echo 'hist:keys=skbaddr.hex:vals=len' > \
+    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+  # echo '!hist:keys=skbaddr.hex:vals=len' > \
+    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  The trigger file itself can be read to show the details of the
+  currently attached hist trigger.  This information is also displayed
+  at the top of the 'hist' file when read.
+
+  By default, the size of the hash table is 2048 entries.  The 'size'
+  parameter can be used to specify more or fewer than that.  The units
+  are in terms of hashtable entries - if a run uses more entries than
+  specified, the results will show the number of 'drops', the number
+  of hits that were ignored.  The size should be a power of 2 between
+  128 and 131072 (any non- power-of-2 number specified will be rounded
+  up).
+
+  The 'sort' parameter can be used to specify a value field to sort
+  on.  The default if unspecified is 'hitcount' and the default sort
+  order is 'ascending'.  To sort in the opposite direction, append
+  .descending' to the sort key.
+
+  The 'pause' parameter can be used to pause an existing hist trigger
+  or to start a hist trigger but not log any events until told to do
+  so.  'continue' or 'cont' can be used to start or restart a paused
+  hist trigger.
+
+  The 'clear' parameter will clear the contents of a running hist
+  trigger and leave its current paused/active state.
+
+  Note that the 'pause', 'cont', and 'clear' parameters should be
+  applied using 'append' shell operator ('>>') if applied to an
+  existing trigger, rather than via the '>' operator, which will cause
+  the trigger to be removed through truncation.
+
+- enable_hist/disable_hist
+
+  The enable_hist and disable_hist triggers can be used to have one
+  event conditionally start and stop another event's already-attached
+  hist trigger.  Any number of enable_hist and disable_hist triggers
+  can be attached to a given event, allowing that event to kick off
+  and stop aggregations on a host of other events.
+
+  The format is very similar to the enable/disable_event triggers:
+
+      enable_hist:<system>:<event>[:count]
+      disable_hist:<system>:<event>[:count]
+
+  Instead of enabling or disabling the tracing of the target event
+  into the trace buffer as the enable/disable_event triggers do, the
+  enable/disable_hist triggers enable or disable the aggregation of
+  the target event into a hash table.
+
+  A typical usage scenario for the enable_hist/disable_hist triggers
+  would be to first set up a paused hist trigger on some event,
+  followed by an enable_hist/disable_hist pair that turns the hist
+  aggregation on and off when conditions of interest are hit:
+
+  # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
+    /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+    /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+  # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+    /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+  The above sets up an initially paused hist trigger which is unpaused
+  and starts aggregating events when a given program is executed, and
+  which stops aggregating when the process exits and the hist trigger
+  is paused again.
+
+  The examples below provide a more concrete illustration of the
+  concepts and typical usage patterns discussed above.
+
+  'special' event fields
+  ------------------------
+
+  There are a number of 'special event fields' available for use as
+  keys or values in a hist trigger.  These look like and behave as if
+  they were actual event fields, but aren't really part of the event's
+  field definition or format file.  They are however available for any
+  event, and can be used anywhere an actual event field could be.
+  They are:
+
+    common_timestamp       u64 - timestamp (from ring buffer) associated
+                                 with the event, in nanoseconds.  May be
+                                modified by .usecs to have timestamps
+                                interpreted as microseconds.
+    cpu                    int - the cpu on which the event occurred.
+
+  Extended error information
+  --------------------------
+
+  For some error conditions encountered when invoking a hist trigger
+  command, extended error information is available via the
+  corresponding event's 'hist' file.  Reading the hist file after an
+  error will display more detailed information about what went wrong,
+  if information is available.  This extended error information will
+  be available until the next hist trigger command for that event.
+
+  If available for a given error condition, the extended error
+  information and usage takes the following form:
+
+    # echo xxx > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
+    echo: write error: Invalid argument
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/hist
+    ERROR: Couldn't yyy: zzz
+      Last command: xxx
+
+6.2 'hist' trigger examples
+---------------------------
+
+  The first set of examples creates aggregations using the kmalloc
+  event.  The fields that can be used for the hist trigger are listed
+  in the kmalloc event's format file:
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
+    name: kmalloc
+    ID: 374
+    format:
+       field:unsigned short common_type;       offset:0;       size:2; signed:0;
+       field:unsigned char common_flags;       offset:2;       size:1; signed:0;
+       field:unsigned char common_preempt_count;               offset:3;       size:1; signed:0;
+       field:int common_pid;                                   offset:4;       size:4; signed:1;
+
+       field:unsigned long call_site;                          offset:8;       size:8; signed:0;
+       field:const void * ptr;                                 offset:16;      size:8; signed:0;
+       field:size_t bytes_req;                                 offset:24;      size:8; signed:0;
+       field:size_t bytes_alloc;                               offset:32;      size:8; signed:0;
+       field:gfp_t gfp_flags;                                  offset:40;      size:4; signed:0;
+
+  We'll start by creating a hist trigger that generates a simple table
+  that lists the total number of bytes requested for each function in
+  the kernel that made one or more calls to kmalloc:
+
+    # echo 'hist:key=call_site:val=bytes_req' > \
+            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+  This tells the tracing system to create a 'hist' trigger using the
+  call_site field of the kmalloc event as the key for the table, which
+  just means that each unique call_site address will have an entry
+  created for it in the table.  The 'val=bytes_req' parameter tells
+  the hist trigger that for each unique entry (call_site) in the
+  table, it should keep a running total of the number of bytes
+  requested by that call_site.
+
+  We'll let it run for awhile and then dump the contents of the 'hist'
+  file in the kmalloc event's subdirectory (for readability, a number
+  of entries have been omitted):
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+    { call_site: 18446744072106379007 } hitcount:          1  bytes_req:        176
+    { call_site: 18446744071579557049 } hitcount:          1  bytes_req:       1024
+    { call_site: 18446744071580608289 } hitcount:          1  bytes_req:      16384
+    { call_site: 18446744071581827654 } hitcount:          1  bytes_req:         24
+    { call_site: 18446744071580700980 } hitcount:          1  bytes_req:          8
+    { call_site: 18446744071579359876 } hitcount:          1  bytes_req:        152
+    { call_site: 18446744071580795365 } hitcount:          3  bytes_req:        144
+    { call_site: 18446744071581303129 } hitcount:          3  bytes_req:        144
+    { call_site: 18446744071580713234 } hitcount:          4  bytes_req:       2560
+    { call_site: 18446744071580933750 } hitcount:          4  bytes_req:        736
+    .
+    .
+    .
+    { call_site: 18446744072106047046 } hitcount:         69  bytes_req:       5576
+    { call_site: 18446744071582116407 } hitcount:         73  bytes_req:       2336
+    { call_site: 18446744072106054684 } hitcount:        136  bytes_req:     140504
+    { call_site: 18446744072106224230 } hitcount:        136  bytes_req:      19584
+    { call_site: 18446744072106078074 } hitcount:        153  bytes_req:       2448
+    { call_site: 18446744072106062406 } hitcount:        153  bytes_req:      36720
+    { call_site: 18446744071582507929 } hitcount:        153  bytes_req:      37088
+    { call_site: 18446744072102520590 } hitcount:        273  bytes_req:      10920
+    { call_site: 18446744071582143559 } hitcount:        358  bytes_req:        716
+    { call_site: 18446744072106465852 } hitcount:        417  bytes_req:      56712
+    { call_site: 18446744072102523378 } hitcount:        485  bytes_req:      27160
+    { call_site: 18446744072099568646 } hitcount:       1676  bytes_req:      33520
+
+    Totals:
+        Hits: 4610
+        Entries: 45
+        Dropped: 0
+
+  The output displays a line for each entry, beginning with the key
+  specified in the trigger, followed by the value(s) also specified in
+  the trigger.  At the beginning of the output is a line that displays
+  the trigger info, which can also be displayed by reading the
+  'trigger' file:
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+    hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+  At the end of the output are a few lines that display the overall
+  totals for the run.  The 'Hits' field shows the total number of
+  times the event trigger was hit, the 'Entries' field shows the total
+  number of used entries in the hash table, and the 'Dropped' field
+  shows the number of hits that were dropped because the number of
+  used entries for the run exceeded the maximum number of entries
+  allowed for the table (normally 0, but if not a hint that you may
+  want to increase the size of the table using the 'size' parameter).
+
+  Notice in the above output that there's an extra field, 'hitcount',
+  which wasn't specified in the trigger.  Also notice that in the
+  trigger info output, there's a parameter, 'sort=hitcount', which
+  wasn't specified in the trigger either.  The reason for that is that
+  every trigger implicitly keeps a count of the total number of hits
+  attributed to a given entry, called the 'hitcount'.  That hitcount
+  information is explicitly displayed in the output, and in the
+  absence of a user-specified sort parameter, is used as the default
+  sort field.
+
+  The value 'hitcount' can be used in place of an explicit value in
+  the 'values' parameter if you don't really need to have any
+  particular field summed and are mainly interested in hit
+  frequencies.
+
+  To turn the hist trigger off, simply call up the trigger in the
+  command history and re-execute it with a '!' prepended:
+
+    # echo '!hist:key=call_site:val=bytes_req' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+  Finally, notice that the call_site as displayed in the output above
+  isn't really very useful.  It's an address, but normally addresses
+  are displayed in hex.  To have a numeric field displayed as a hex
+  value, simply append '.hex' to the field name in the trigger:
+
+    # echo 'hist:key=call_site.hex:val=bytes_req' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.hex:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+    { call_site: ffffffffa026b291 } hitcount:          1  bytes_req:        433
+    { call_site: ffffffffa07186ff } hitcount:          1  bytes_req:        176
+    { call_site: ffffffff811ae721 } hitcount:          1  bytes_req:      16384
+    { call_site: ffffffff811c5134 } hitcount:          1  bytes_req:          8
+    { call_site: ffffffffa04a9ebb } hitcount:          1  bytes_req:        511
+    { call_site: ffffffff8122e0a6 } hitcount:          1  bytes_req:         12
+    { call_site: ffffffff8107da84 } hitcount:          1  bytes_req:        152
+    { call_site: ffffffff812d8246 } hitcount:          1  bytes_req:         24
+    { call_site: ffffffff811dc1e5 } hitcount:          3  bytes_req:        144
+    { call_site: ffffffffa02515e8 } hitcount:          3  bytes_req:        648
+    { call_site: ffffffff81258159 } hitcount:          3  bytes_req:        144
+    { call_site: ffffffff811c80f4 } hitcount:          4  bytes_req:        544
+    .
+    .
+    .
+    { call_site: ffffffffa06c7646 } hitcount:        106  bytes_req:       8024
+    { call_site: ffffffffa06cb246 } hitcount:        132  bytes_req:      31680
+    { call_site: ffffffffa06cef7a } hitcount:        132  bytes_req:       2112
+    { call_site: ffffffff8137e399 } hitcount:        132  bytes_req:      23232
+    { call_site: ffffffffa06c941c } hitcount:        185  bytes_req:     171360
+    { call_site: ffffffffa06f2a66 } hitcount:        185  bytes_req:      26640
+    { call_site: ffffffffa036a70e } hitcount:        265  bytes_req:      10600
+    { call_site: ffffffff81325447 } hitcount:        292  bytes_req:        584
+    { call_site: ffffffffa072da3c } hitcount:        446  bytes_req:      60656
+    { call_site: ffffffffa036b1f2 } hitcount:        526  bytes_req:      29456
+    { call_site: ffffffffa0099c06 } hitcount:       1780  bytes_req:      35600
+
+    Totals:
+        Hits: 4775
+        Entries: 46
+        Dropped: 0
+
+  Even that's only marginally more useful - while hex values do look
+  more like addresses, what users are typically more interested in
+  when looking at text addresses are the corresponding symbols
+  instead.  To have an address displayed as symbolic value instead,
+  simply append '.sym' or '.sym-offset' to the field name in the
+  trigger:
+
+    # echo 'hist:key=call_site.sym:val=bytes_req' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+    { call_site: [ffffffff810adcb9] syslog_print_all                              } hitcount:          1  bytes_req:       1024
+    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffff8154acbe] usb_alloc_urb                                 } hitcount:          1  bytes_req:        192
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
+    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff811febd5] fsnotify_alloc_group                          } hitcount:          2  bytes_req:        528
+    { call_site: [ffffffff81440f58] __tty_buffer_request_room                     } hitcount:          2  bytes_req:       2624
+    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          2  bytes_req:         96
+    { call_site: [ffffffffa05e19af] ieee80211_start_tx_ba_session [mac80211]      } hitcount:          2  bytes_req:        464
+    { call_site: [ffffffff81672406] tcp_get_metrics                               } hitcount:          2  bytes_req:        304
+    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff81089b05] sched_create_group                            } hitcount:          2  bytes_req:       1424
+    .
+    .
+    .
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1185  bytes_req:     123240
+    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:       1185  bytes_req:     104280
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       1402  bytes_req:     190672
+    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       1518  bytes_req:     146208
+    { call_site: [ffffffffa029070e] drm_vma_node_allow [drm]                      } hitcount:       1746  bytes_req:      69840
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       2021  bytes_req:     792312
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       2592  bytes_req:     145152
+    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2629  bytes_req:     378576
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2629  bytes_req:    3783248
+    { call_site: [ffffffff81325607] apparmor_file_alloc_security                  } hitcount:       5192  bytes_req:      10384
+    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       5529  bytes_req:     110584
+    { call_site: [ffffffff8131ebf7] aa_alloc_task_context                         } hitcount:      21943  bytes_req:     702176
+    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:      55759  bytes_req:    5074265
+
+    Totals:
+        Hits: 109928
+        Entries: 71
+        Dropped: 0
+
+  Because the default sort key above is 'hitcount', the above shows a
+  the list of call_sites by increasing hitcount, so that at the bottom
+  we see the functions that made the most kmalloc calls during the
+  run.  If instead we we wanted to see the top kmalloc callers in
+  terms of the number of bytes requested rather than the number of
+  calls, and we wanted the top caller to appear at the top, we can use
+  the 'sort' parameter, along with the 'descending' modifier:
+
+    # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
+
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2186  bytes_req:    3397464
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1790  bytes_req:     712176
+    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       8132  bytes_req:     513135
+    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        106  bytes_req:     440128
+    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2186  bytes_req:     314784
+    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       2174  bytes_req:     208992
+    { call_site: [ffffffff811ae8e1] __kmalloc                                     } hitcount:          8  bytes_req:     131072
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:        859  bytes_req:     116824
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       1834  bytes_req:     102704
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:        972  bytes_req:     101088
+    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:        972  bytes_req:      85536
+    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       3333  bytes_req:      66664
+    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        209  bytes_req:      61632
+    .
+    .
+    .
+    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff812d8406] copy_semundo                                  } hitcount:          2  bytes_req:         48
+    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          1  bytes_req:         48
+    { call_site: [ffffffffa027121a] drm_getmagic [drm]                            } hitcount:          1  bytes_req:         48
+    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
+    { call_site: [ffffffff811c52f4] bprm_change_interp                            } hitcount:          2  bytes_req:         16
+    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
+
+    Totals:
+        Hits: 32133
+        Entries: 81
+        Dropped: 0
+
+  To display the offset and size information in addition to the symbol
+  name, just use 'sym-offset' instead:
+
+    # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym-offset:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
+
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2+0x6c/0x2c0 [i915]                  } hitcount:       4569  bytes_req:    3163720
+    { call_site: [ffffffffa0489a66] intel_ring_begin+0xc6/0x1f0 [i915]                      } hitcount:       4569  bytes_req:     657936
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23+0x694/0x1020 [i915]      } hitcount:       1519  bytes_req:     472936
+    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23+0x516/0x1020 [i915]      } hitcount:       3050  bytes_req:     211832
+    { call_site: [ffffffff811e2a1b] seq_buf_alloc+0x1b/0x50                                 } hitcount:         34  bytes_req:     148384
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip+0xbc/0x870 [i915]                  } hitcount:       1385  bytes_req:     144040
+    { call_site: [ffffffff811ae8e1] __kmalloc+0x191/0x1b0                                   } hitcount:          8  bytes_req:     131072
+    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl+0x282/0x360 [drm]              } hitcount:       1385  bytes_req:     121880
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc+0x32/0x100 [drm]                  } hitcount:       1848  bytes_req:     103488
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state+0x2c/0xa0 [i915]            } hitcount:        461  bytes_req:      62696
+    { call_site: [ffffffffa029070e] drm_vma_node_allow+0x2e/0xd0 [drm]                      } hitcount:       1541  bytes_req:      61640
+    { call_site: [ffffffff815f8d7b] sk_prot_alloc+0xcb/0x1b0                                } hitcount:         57  bytes_req:      57456
+    .
+    .
+    .
+    { call_site: [ffffffff8109524a] alloc_fair_sched_group+0x5a/0x1a0                       } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffffa027b921] drm_vm_open_locked+0x31/0xa0 [drm]                      } hitcount:          3  bytes_req:         96
+    { call_site: [ffffffff8122e266] proc_self_follow_link+0x76/0xb0                         } hitcount:          8  bytes_req:         96
+    { call_site: [ffffffff81213e80] load_elf_binary+0x240/0x1650                            } hitcount:          3  bytes_req:         84
+    { call_site: [ffffffff8154bc62] usb_control_msg+0x42/0x110                              } hitcount:          1  bytes_req:          8
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report+0x7e/0x1a0 [hid]                     } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event+0x8a/0x120 [hid]                    } hitcount:          1  bytes_req:          7
+
+    Totals:
+        Hits: 26098
+        Entries: 64
+        Dropped: 0
+
+  We can also add multiple fields to the 'values' parameter.  For
+  example, we might want to see the total number of bytes allocated
+  alongside bytes requested, and display the result sorted by bytes
+  allocated in a descending order:
+
+    # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym:vals=bytes_req,bytes_alloc:sort=bytes_alloc.descending:size=2048 [active]
+
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       7403  bytes_req:    4084360  bytes_alloc:    5958016
+    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        541  bytes_req:    2213968  bytes_alloc:    2228224
+    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       7404  bytes_req:    1066176  bytes_alloc:    1421568
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1565  bytes_req:     557368  bytes_alloc:    1037760
+    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       9557  bytes_req:     595778  bytes_alloc:     695744
+    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       5839  bytes_req:     430680  bytes_alloc:     470400
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       2388  bytes_req:     324768  bytes_alloc:     458496
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       3911  bytes_req:     219016  bytes_alloc:     250304
+    { call_site: [ffffffff815f8d7b] sk_prot_alloc                                 } hitcount:        235  bytes_req:     236880  bytes_alloc:     240640
+    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        557  bytes_req:     169024  bytes_alloc:     221760
+    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       9378  bytes_req:     187548  bytes_alloc:     206312
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1519  bytes_req:     157976  bytes_alloc:     194432
+    .
+    .
+    .
+    { call_site: [ffffffff8109bd3b] sched_autogroup_create_attach                 } hitcount:          2  bytes_req:        144  bytes_alloc:        192
+    { call_site: [ffffffff81097ee8] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff81213e80] load_elf_binary                               } hitcount:          3  bytes_req:         84  bytes_alloc:         96
+    { call_site: [ffffffff81079a2e] kthread_create_on_node                        } hitcount:          1  bytes_req:         56  bytes_alloc:         64
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7  bytes_alloc:          8
+    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8  bytes_alloc:          8
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7  bytes_alloc:          8
+
+    Totals:
+        Hits: 66598
+        Entries: 65
+        Dropped: 0
+
+  Finally, to finish off our kmalloc example, instead of simply having
+  the hist trigger display symbolic call_sites, we can have the hist
+  trigger additionally display the complete set of kernel stack traces
+  that led to each call_site.  To do that, we simply use the special
+  value 'stacktrace' for the key parameter:
+
+    # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+  The above trigger will use the kernel stack trace in effect when an
+  event is triggered as the key for the hash table.  This allows the
+  enumeration of every kernel callpath that led up to a particular
+  event, along with a running total of any of the event fields for
+  that event.  Here we tally bytes requested and bytes allocated for
+  every callpath in the system that led up to a kmalloc (in this case
+  every callpath to a kmalloc for a kernel compile):
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
+
+    { stacktrace:
+         __kmalloc_track_caller+0x10b/0x1a0
+         kmemdup+0x20/0x50
+         hidraw_report_event+0x8a/0x120 [hid]
+         hid_report_raw_event+0x3ea/0x440 [hid]
+         hid_input_report+0x112/0x190 [hid]
+         hid_irq_in+0xc2/0x260 [usbhid]
+         __usb_hcd_giveback_urb+0x72/0x120
+         usb_giveback_urb_bh+0x9e/0xe0
+         tasklet_hi_action+0xf8/0x100
+         __do_softirq+0x114/0x2c0
+         irq_exit+0xa5/0xb0
+         do_IRQ+0x5a/0xf0
+         ret_from_intr+0x0/0x30
+         cpuidle_enter+0x17/0x20
+         cpu_startup_entry+0x315/0x3e0
+         rest_init+0x7c/0x80
+    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
+    { stacktrace:
+         __kmalloc_track_caller+0x10b/0x1a0
+         kmemdup+0x20/0x50
+         hidraw_report_event+0x8a/0x120 [hid]
+         hid_report_raw_event+0x3ea/0x440 [hid]
+         hid_input_report+0x112/0x190 [hid]
+         hid_irq_in+0xc2/0x260 [usbhid]
+         __usb_hcd_giveback_urb+0x72/0x120
+         usb_giveback_urb_bh+0x9e/0xe0
+         tasklet_hi_action+0xf8/0x100
+         __do_softirq+0x114/0x2c0
+         irq_exit+0xa5/0xb0
+         do_IRQ+0x5a/0xf0
+         ret_from_intr+0x0/0x30
+    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
+    { stacktrace:
+         kmem_cache_alloc_trace+0xeb/0x150
+         aa_alloc_task_context+0x27/0x40
+         apparmor_cred_prepare+0x1f/0x50
+         security_prepare_creds+0x16/0x20
+         prepare_creds+0xdf/0x1a0
+         SyS_capset+0xb5/0x200
+         system_call_fastpath+0x12/0x6a
+    } hitcount:          1  bytes_req:         32  bytes_alloc:         32
+    .
+    .
+    .
+    { stacktrace:
+         __kmalloc+0x11b/0x1b0
+         i915_gem_execbuffer2+0x6c/0x2c0 [i915]
+         drm_ioctl+0x349/0x670 [drm]
+         do_vfs_ioctl+0x2f0/0x4f0
+         SyS_ioctl+0x81/0xa0
+         system_call_fastpath+0x12/0x6a
+    } hitcount:      17726  bytes_req:   13944120  bytes_alloc:   19593808
+    { stacktrace:
+         __kmalloc+0x11b/0x1b0
+         load_elf_phdrs+0x76/0xa0
+         load_elf_binary+0x102/0x1650
+         search_binary_handler+0x97/0x1d0
+         do_execveat_common.isra.34+0x551/0x6e0
+         SyS_execve+0x3a/0x50
+         return_from_execve+0x0/0x23
+    } hitcount:      33348  bytes_req:   17152128  bytes_alloc:   20226048
+    { stacktrace:
+         kmem_cache_alloc_trace+0xeb/0x150
+         apparmor_file_alloc_security+0x27/0x40
+         security_file_alloc+0x16/0x20
+         get_empty_filp+0x93/0x1c0
+         path_openat+0x31/0x5f0
+         do_filp_open+0x3a/0x90
+         do_sys_open+0x128/0x220
+         SyS_open+0x1e/0x20
+         system_call_fastpath+0x12/0x6a
+    } hitcount:    4766422  bytes_req:    9532844  bytes_alloc:   38131376
+    { stacktrace:
+         __kmalloc+0x11b/0x1b0
+         seq_buf_alloc+0x1b/0x50
+         seq_read+0x2cc/0x370
+         proc_reg_read+0x3d/0x80
+         __vfs_read+0x28/0xe0
+         vfs_read+0x86/0x140
+         SyS_read+0x46/0xb0
+         system_call_fastpath+0x12/0x6a
+    } hitcount:      19133  bytes_req:   78368768  bytes_alloc:   78368768
+
+    Totals:
+        Hits: 6085872
+        Entries: 253
+        Dropped: 0
+
+  If you key a hist trigger on common_pid, in order for example to
+  gather and display sorted totals for each process, you can use the
+  special .execname modifier to display the executable names for the
+  processes in the table rather than raw pids.  The example below
+  keeps a per-process sum of total bytes read:
+
+    # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
+           /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
+
+    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/hist
+    # trigger info: hist:keys=common_pid.execname:vals=count:sort=count.descending:size=2048 [active]
+
+    { common_pid: gnome-terminal  [      3196] } hitcount:        280  count:    1093512
+    { common_pid: Xorg            [      1309] } hitcount:        525  count:     256640
+    { common_pid: compiz          [      2889] } hitcount:         59  count:     254400
+    { common_pid: bash            [      8710] } hitcount:          3  count:      66369
+    { common_pid: dbus-daemon-lau [      8703] } hitcount:         49  count:      47739
+    { common_pid: irqbalance      [      1252] } hitcount:         27  count:      27648
+    { common_pid: 01ifupdown      [      8705] } hitcount:          3  count:      17216
+    { common_pid: dbus-daemon     [       772] } hitcount:         10  count:      12396
+    { common_pid: Socket Thread   [      8342] } hitcount:         11  count:      11264
+    { common_pid: nm-dhcp-client. [      8701] } hitcount:          6  count:       7424
+    { common_pid: gmain           [      1315] } hitcount:         18  count:       6336
+    .
+    .
+    .
+    { common_pid: postgres        [      1892] } hitcount:          2  count:         32
+    { common_pid: postgres        [      1891] } hitcount:          2  count:         32
+    { common_pid: gmain           [      8704] } hitcount:          2  count:         32
+    { common_pid: upstart-dbus-br [      2740] } hitcount:         21  count:         21
+    { common_pid: nm-dispatcher.a [      8696] } hitcount:          1  count:         16
+    { common_pid: indicator-datet [      2904] } hitcount:          1  count:         16
+    { common_pid: gdbus           [      2998] } hitcount:          1  count:         16
+    { common_pid: rtkit-daemon    [      2052] } hitcount:          1  count:          8
+    { common_pid: init            [         1] } hitcount:          2  count:          2
+
+    Totals:
+        Hits: 2116
+        Entries: 51
+        Dropped: 0
+
+  Similarly, if you key a hist trigger on syscall id, for example to
+  gather and display a list of systemwide syscall hits, you can use
+  the special .syscall modifier to display the syscall names rather
+  than raw ids.  The example below keeps a running total of syscall
+  counts for the system during the run:
+
+    # echo 'hist:key=id.syscall:val=hitcount' > \
+           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+    # trigger info: hist:keys=id.syscall:vals=hitcount:sort=hitcount:size=2048 [active]
+
+    { id: sys_fsync                     [ 74] } hitcount:          1
+    { id: sys_newuname                  [ 63] } hitcount:          1
+    { id: sys_prctl                     [157] } hitcount:          1
+    { id: sys_statfs                    [137] } hitcount:          1
+    { id: sys_symlink                   [ 88] } hitcount:          1
+    { id: sys_sendmmsg                  [307] } hitcount:          1
+    { id: sys_semctl                    [ 66] } hitcount:          1
+    { id: sys_readlink                  [ 89] } hitcount:          3
+    { id: sys_bind                      [ 49] } hitcount:          3
+    { id: sys_getsockname               [ 51] } hitcount:          3
+    { id: sys_unlink                    [ 87] } hitcount:          3
+    { id: sys_rename                    [ 82] } hitcount:          4
+    { id: unknown_syscall               [ 58] } hitcount:          4
+    { id: sys_connect                   [ 42] } hitcount:          4
+    { id: sys_getpid                    [ 39] } hitcount:          4
+    .
+    .
+    .
+    { id: sys_rt_sigprocmask            [ 14] } hitcount:        952
+    { id: sys_futex                     [202] } hitcount:       1534
+    { id: sys_write                     [  1] } hitcount:       2689
+    { id: sys_setitimer                 [ 38] } hitcount:       2797
+    { id: sys_read                      [  0] } hitcount:       3202
+    { id: sys_select                    [ 23] } hitcount:       3773
+    { id: sys_writev                    [ 20] } hitcount:       4531
+    { id: sys_poll                      [  7] } hitcount:       8314
+    { id: sys_recvmsg                   [ 47] } hitcount:      13738
+    { id: sys_ioctl                     [ 16] } hitcount:      21843
+
+    Totals:
+        Hits: 67612
+        Entries: 72
+        Dropped: 0
+
+    The syscall counts above provide a rough overall picture of system
+    call activity on the system; we can see for example that the most
+    popular system call on this system was the 'sys_ioctl' system call.
+
+    We can use 'compound' keys to refine that number and provide some
+    further insight as to which processes exactly contribute to the
+    overall ioctl count.
+
+    The command below keeps a hitcount for every unique combination of
+    system call id and pid - the end result is essentially a table
+    that keeps a per-pid sum of system call hits.  The results are
+    sorted using the system call id as the primary key, and the
+    hitcount sum as the secondary key:
+
+    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
+           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 [active]
+
+    { id: sys_read                      [  0], common_pid: rtkit-daemon    [      1877] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: gdbus           [      2976] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: console-kit-dae [      3400] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: postgres        [      1865] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: deja-dup-monito [      3543] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: NetworkManager  [       890] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: evolution-calen [      3048] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: postgres        [      1864] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: nm-applet       [      3022] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: whoopsie        [      1212] } hitcount:          2
+    .
+    .
+    .
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      8479] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      3472] } hitcount:         12
+    { id: sys_ioctl                     [ 16], common_pid: gnome-terminal  [      3199] } hitcount:         16
+    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:       1808
+    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:       5580
+    .
+    .
+    .
+    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2690] } hitcount:          3
+    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2688] } hitcount:         16
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [       975] } hitcount:          2
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3204] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2888] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3003] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2873] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3196] } hitcount:          6
+    { id: sys_openat                    [257], common_pid: java            [      2623] } hitcount:          2
+    { id: sys_eventfd2                  [290], common_pid: ibus-ui-gtk3    [      2760] } hitcount:          4
+    { id: sys_eventfd2                  [290], common_pid: compiz          [      2994] } hitcount:          6
+
+    Totals:
+        Hits: 31536
+        Entries: 323
+        Dropped: 0
+
+    The above list does give us a breakdown of the ioctl syscall by
+    pid, but it also gives us quite a bit more than that, which we
+    don't really care about at the moment.  Since we know the syscall
+    id for sys_ioctl (16, displayed next to the sys_ioctl name), we
+    can use that to filter out all the other syscalls:
+
+    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
+           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 if id == 16 [active]
+
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2769] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: evolution-addre [      8571] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      3003] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2781] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2829] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      8726] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      8508] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2970] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2768] } hitcount:          1
+    .
+    .
+    .
+    { id: sys_ioctl                     [ 16], common_pid: pool            [      8559] } hitcount:         45
+    { id: sys_ioctl                     [ 16], common_pid: pool            [      8555] } hitcount:         48
+    { id: sys_ioctl                     [ 16], common_pid: pool            [      8551] } hitcount:         48
+    { id: sys_ioctl                     [ 16], common_pid: avahi-daemon    [       896] } hitcount:         66
+    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:      26674
+    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:      73443
+
+    Totals:
+        Hits: 101162
+        Entries: 103
+        Dropped: 0
+
+    The above output shows that 'compiz' and 'Xorg' are far and away
+    the heaviest ioctl callers (which might lead to questions about
+    whether they really need to be making all those calls and to
+    possible avenues for further investigation.)
+
+    The compound key examples used a key and a sum value (hitcount) to
+    sort the output, but we can just as easily use two keys instead.
+    Here's an example where we use a compound key composed of the the
+    common_pid and size event fields.  Sorting with pid as the primary
+    key and 'size' as the secondary key allows us to display an
+    ordered summary of the recvfrom sizes, with counts, received by
+    each process:
+
+    # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
+           /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
+
+    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/hist
+    # trigger info: hist:keys=common_pid.execname,size:vals=hitcount:sort=common_pid.execname,size:size=2048 [active]
+
+    { common_pid: smbd            [       784], size:          4 } hitcount:          1
+    { common_pid: dnsmasq         [      1412], size:       4096 } hitcount:        672
+    { common_pid: postgres        [      1796], size:       1000 } hitcount:          6
+    { common_pid: postgres        [      1867], size:       1000 } hitcount:         10
+    { common_pid: bamfdaemon      [      2787], size:         28 } hitcount:          2
+    { common_pid: bamfdaemon      [      2787], size:      14360 } hitcount:          1
+    { common_pid: compiz          [      2994], size:          8 } hitcount:          1
+    { common_pid: compiz          [      2994], size:         20 } hitcount:         11
+    { common_pid: gnome-terminal  [      3199], size:          4 } hitcount:          2
+    { common_pid: firefox         [      8817], size:          4 } hitcount:          1
+    { common_pid: firefox         [      8817], size:          8 } hitcount:          5
+    { common_pid: firefox         [      8817], size:        588 } hitcount:          2
+    { common_pid: firefox         [      8817], size:        628 } hitcount:          1
+    { common_pid: firefox         [      8817], size:       6944 } hitcount:          1
+    { common_pid: firefox         [      8817], size:     408880 } hitcount:          2
+    { common_pid: firefox         [      8822], size:          8 } hitcount:          2
+    { common_pid: firefox         [      8822], size:        160 } hitcount:          2
+    { common_pid: firefox         [      8822], size:        320 } hitcount:          2
+    { common_pid: firefox         [      8822], size:        352 } hitcount:          1
+    .
+    .
+    .
+    { common_pid: pool            [      8923], size:       1960 } hitcount:         10
+    { common_pid: pool            [      8923], size:       2048 } hitcount:         10
+    { common_pid: pool            [      8924], size:       1960 } hitcount:         10
+    { common_pid: pool            [      8924], size:       2048 } hitcount:         10
+    { common_pid: pool            [      8928], size:       1964 } hitcount:          4
+    { common_pid: pool            [      8928], size:       1965 } hitcount:          2
+    { common_pid: pool            [      8928], size:       2048 } hitcount:          6
+    { common_pid: pool            [      8929], size:       1982 } hitcount:          1
+    { common_pid: pool            [      8929], size:       2048 } hitcount:          1
+
+    Totals:
+        Hits: 2016
+        Entries: 224
+        Dropped: 0
+
+  The above example also illustrates the fact that although a compound
+  key is treated as a single entity for hashing purposes, the sub-keys
+  it's composed of can be accessed independently.
+
+  The next example uses a string field as the hash key and
+  demonstrates how you can manually pause and continue a hist trigger.
+  In this example, we'll aggregate fork counts and don't expect a
+  large number of entries in the hash table, so we'll drop it to a
+  much smaller number, say 256:
+
+    # echo 'hist:key=child_comm:val=hitcount:size=256' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
+
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: ibus-daemon                         } hitcount:          1
+    { child_comm: whoopsie                            } hitcount:          1
+    { child_comm: smbd                                } hitcount:          1
+    { child_comm: gdbus                               } hitcount:          1
+    { child_comm: kthreadd                            } hitcount:          1
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: evolution-alarm                     } hitcount:          2
+    { child_comm: Socket Thread                       } hitcount:          2
+    { child_comm: postgres                            } hitcount:          2
+    { child_comm: bash                                } hitcount:          3
+    { child_comm: compiz                              } hitcount:          3
+    { child_comm: evolution-sourc                     } hitcount:          4
+    { child_comm: dhclient                            } hitcount:          4
+    { child_comm: pool                                } hitcount:          5
+    { child_comm: nm-dispatcher.a                     } hitcount:          8
+    { child_comm: firefox                             } hitcount:          8
+    { child_comm: dbus-daemon                         } hitcount:          8
+    { child_comm: glib-pacrunner                      } hitcount:         10
+    { child_comm: evolution                           } hitcount:         23
+
+    Totals:
+        Hits: 89
+        Entries: 20
+        Dropped: 0
+
+  If we want to pause the hist trigger, we can simply append :pause to
+  the command that started the trigger.  Notice that the trigger info
+  displays as [paused]:
+
+    # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [paused]
+
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: kthreadd                            } hitcount:          1
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: gdbus                               } hitcount:          1
+    { child_comm: ibus-daemon                         } hitcount:          1
+    { child_comm: Socket Thread                       } hitcount:          2
+    { child_comm: evolution-alarm                     } hitcount:          2
+    { child_comm: smbd                                } hitcount:          2
+    { child_comm: bash                                } hitcount:          3
+    { child_comm: whoopsie                            } hitcount:          3
+    { child_comm: compiz                              } hitcount:          3
+    { child_comm: evolution-sourc                     } hitcount:          4
+    { child_comm: pool                                } hitcount:          5
+    { child_comm: postgres                            } hitcount:          6
+    { child_comm: firefox                             } hitcount:          8
+    { child_comm: dhclient                            } hitcount:         10
+    { child_comm: emacs                               } hitcount:         12
+    { child_comm: dbus-daemon                         } hitcount:         20
+    { child_comm: nm-dispatcher.a                     } hitcount:         20
+    { child_comm: evolution                           } hitcount:         35
+    { child_comm: glib-pacrunner                      } hitcount:         59
+
+    Totals:
+        Hits: 199
+        Entries: 21
+        Dropped: 0
+
+  To manually continue having the trigger aggregate events, append
+  :cont instead.  Notice that the trigger info displays as [active]
+  again, and the data has changed:
+
+    # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
+
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: kthreadd                            } hitcount:          1
+    { child_comm: gdbus                               } hitcount:          1
+    { child_comm: ibus-daemon                         } hitcount:          1
+    { child_comm: Socket Thread                       } hitcount:          2
+    { child_comm: evolution-alarm                     } hitcount:          2
+    { child_comm: smbd                                } hitcount:          2
+    { child_comm: whoopsie                            } hitcount:          3
+    { child_comm: compiz                              } hitcount:          3
+    { child_comm: evolution-sourc                     } hitcount:          4
+    { child_comm: bash                                } hitcount:          5
+    { child_comm: pool                                } hitcount:          5
+    { child_comm: postgres                            } hitcount:          6
+    { child_comm: firefox                             } hitcount:          8
+    { child_comm: dhclient                            } hitcount:         11
+    { child_comm: emacs                               } hitcount:         12
+    { child_comm: dbus-daemon                         } hitcount:         22
+    { child_comm: nm-dispatcher.a                     } hitcount:         22
+    { child_comm: evolution                           } hitcount:         35
+    { child_comm: glib-pacrunner                      } hitcount:         59
+
+    Totals:
+        Hits: 206
+        Entries: 21
+        Dropped: 0
+
+  The previous example showed how to start and stop a hist trigger by
+  appending 'pause' and 'continue' to the hist trigger command.  A
+  hist trigger can also be started in a paused state by initially
+  starting the trigger with ':pause' appended.  This allows you to
+  start the trigger only when you're ready to start collecting data
+  and not before.  For example, you could start the trigger in a
+  paused state, then unpause it and do something you want to measure,
+  then pause the trigger again when done.
+
+  Of course, doing this manually can be difficult and error-prone, but
+  it is possible to automatically start and stop a hist trigger based
+  on some condition, via the enable_hist and disable_hist triggers.
+
+  For example, suppose we wanted to take a look at the relative
+  weights in terms of skb length for each callpath that leads to a
+  netif_receieve_skb event when downloading a decent-sized file using
+  wget.
+
+  First we set up an initially paused stacktrace trigger on the
+  netif_receive_skb event:
+
+    # echo 'hist:key=stacktrace:vals=len:pause' > \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  Next, we set up an 'enable_hist' trigger on the sched_process_exec
+  event, with an 'if filename==/usr/bin/wget' filter.  The effect of
+  this new trigger is that it will 'unpause' the hist trigger we just
+  set up on netif_receive_skb if and only if it sees a
+  sched_process_exec event with a filename of '/usr/bin/wget'.  When
+  that happens, all netif_receive_skb events are aggregated into a
+  hash table keyed on stacktrace:
+
+    # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+  The aggregation continues until the netif_receive_skb is paused
+  again, which is what the following disable_hist event does by
+  creating a similar setup on the sched_process_exit event, using the
+  filter 'comm==wget':
+
+    # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+  Whenever a process exits and the comm field of the disable_hist
+  trigger filter matches 'comm==wget', the netif_receive_skb hist
+  trigger is disabled.
+
+  The overall effect is that netif_receive_skb events are aggregated
+  into the hash table for only the duration of the wget.  Executing a
+  wget command and then listing the 'hist' file will display the
+  output generated by the wget command:
+
+    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
+
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         netif_receive_skb_internal+0x23/0x90
+         napi_gro_receive+0xc8/0x100
+         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
+         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
+         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
+         ieee80211_rx+0x31d/0x900 [mac80211]
+         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
+         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
+         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
+         irq_thread_fn+0x20/0x50
+         irq_thread+0x11f/0x150
+         kthread+0xd2/0xf0
+         ret_from_fork+0x42/0x70
+    } hitcount:         85  len:      28884
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         netif_receive_skb_internal+0x23/0x90
+         napi_gro_complete+0xa4/0xe0
+         dev_gro_receive+0x23a/0x360
+         napi_gro_receive+0x30/0x100
+         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
+         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
+         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
+         ieee80211_rx+0x31d/0x900 [mac80211]
+         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
+         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
+         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
+         irq_thread_fn+0x20/0x50
+         irq_thread+0x11f/0x150
+         kthread+0xd2/0xf0
+    } hitcount:         98  len:     664329
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         process_backlog+0xa8/0x150
+         net_rx_action+0x15d/0x340
+         __do_softirq+0x114/0x2c0
+         do_softirq_own_stack+0x1c/0x30
+         do_softirq+0x65/0x70
+         __local_bh_enable_ip+0xb5/0xc0
+         ip_finish_output+0x1f4/0x840
+         ip_output+0x6b/0xc0
+         ip_local_out_sk+0x31/0x40
+         ip_send_skb+0x1a/0x50
+         udp_send_skb+0x173/0x2a0
+         udp_sendmsg+0x2bf/0x9f0
+         inet_sendmsg+0x64/0xa0
+         sock_sendmsg+0x3d/0x50
+    } hitcount:        115  len:      13030
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         netif_receive_skb_internal+0x23/0x90
+         napi_gro_complete+0xa4/0xe0
+         napi_gro_flush+0x6d/0x90
+         iwl_pcie_irq_handler+0x92a/0x12f0 [iwlwifi]
+         irq_thread_fn+0x20/0x50
+         irq_thread+0x11f/0x150
+         kthread+0xd2/0xf0
+         ret_from_fork+0x42/0x70
+    } hitcount:        934  len:    5512212
+
+    Totals:
+        Hits: 1232
+        Entries: 4
+        Dropped: 0
+
+  The above shows all the netif_receive_skb callpaths and their total
+  lengths for the duration of the wget command.
+
+  The 'clear' hist trigger param can be used to clear the hash table.
+  Suppose we wanted to try another run of the previous example but
+  this time also wanted to see the complete list of events that went
+  into the histogram.  In order to avoid having to set everything up
+  again, we can just clear the histogram first:
+
+    # echo 'hist:key=stacktrace:vals=len:clear' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  Just to verify that it is in fact cleared, here's what we now see in
+  the hist file:
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
+
+    Totals:
+        Hits: 0
+        Entries: 0
+        Dropped: 0
+
+  Since we want to see the detailed list of every netif_receive_skb
+  event occurring during the new run, which are in fact the same
+  events being aggregated into the hash table, we add some additional
+  'enable_event' events to the triggering sched_process_exec and
+  sched_process_exit events as such:
+
+    # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+    # echo 'disable_event:net:netif_receive_skb if comm==wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+  If you read the trigger files for the sched_process_exec and
+  sched_process_exit triggers, you should see two triggers for each:
+  one enabling/disabling the hist aggregation and the other
+  enabling/disabling the logging of events:
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+    enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
+    enable_hist:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+    enable_event:net:netif_receive_skb:unlimited if comm==wget
+    disable_hist:net:netif_receive_skb:unlimited if comm==wget
+
+  In other words, whenever either of the sched_process_exec or
+  sched_process_exit events is hit and matches 'wget', it enables or
+  disables both the histogram and the event log, and what you end up
+  with is a hash table and set of events just covering the specified
+  duration.  Run the wget command again:
+
+    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
+
+  Displaying the 'hist' file should show something similar to what you
+  saw in the last run, but this time you should also see the
+  individual events in the trace file:
+
+    # cat /sys/kernel/debug/tracing/trace
+
+    # tracer: nop
+    #
+    # entries-in-buffer/entries-written: 183/1426   #P:4
+    #
+    #                              _-----=> irqs-off
+    #                             / _----=> need-resched
+    #                            | / _---=> hardirq/softirq
+    #                            || / _--=> preempt-depth
+    #                            ||| /     delay
+    #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+    #              | |       |   ||||       |         |
+                wget-15108 [000] ..s1 31769.606929: netif_receive_skb: dev=lo skbaddr=ffff88009c353100 len=60
+                wget-15108 [000] ..s1 31769.606999: netif_receive_skb: dev=lo skbaddr=ffff88009c353200 len=60
+             dnsmasq-1382  [000] ..s1 31769.677652: netif_receive_skb: dev=lo skbaddr=ffff88009c352b00 len=130
+             dnsmasq-1382  [000] ..s1 31769.685917: netif_receive_skb: dev=lo skbaddr=ffff88009c352200 len=138
+    ##### CPU 2 buffer started ####
+      irq/29-iwlwifi-559   [002] ..s. 31772.031529: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433d00 len=2948
+      irq/29-iwlwifi-559   [002] ..s. 31772.031572: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432200 len=1500
+      irq/29-iwlwifi-559   [002] ..s. 31772.032196: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433100 len=2948
+      irq/29-iwlwifi-559   [002] ..s. 31772.032761: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433000 len=2948
+      irq/29-iwlwifi-559   [002] ..s. 31772.033220: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432e00 len=1500
+    .
+    .
+    .
+
+  The following example demonstrates how multiple hist triggers can be
+  attached to a given event.  This capability can be useful for
+  creating a set of different summaries derived from the same set of
+  events, or for comparing the effects of different filters, among
+  other things.
+
+    # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len if len > 4096' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len if len == 256' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=len:vals=common_preempt_count' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  The above set of commands create four triggers differing only in
+  their filters, along with a completely different though fairly
+  nonsensical trigger.  Note that in order to append multiple hist
+  triggers to the same file, you should use the '>>' operator to
+  append them ('>' will also add the new hist trigger, but will remove
+  any existing hist triggers beforehand).
+
+  Displaying the contents of the 'hist' file for the event shows the
+  contents of all five histograms:
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+
+    # event histogram
+    #
+    # trigger info: hist:keys=len:vals=hitcount,common_preempt_count:sort=hitcount:size=2048 [active]
+    #
+
+    { len:        176 } hitcount:          1  common_preempt_count:          0
+    { len:        223 } hitcount:          1  common_preempt_count:          0
+    { len:       4854 } hitcount:          1  common_preempt_count:          0
+    { len:        395 } hitcount:          1  common_preempt_count:          0
+    { len:        177 } hitcount:          1  common_preempt_count:          0
+    { len:        446 } hitcount:          1  common_preempt_count:          0
+    { len:       1601 } hitcount:          1  common_preempt_count:          0
+    .
+    .
+    .
+    { len:       1280 } hitcount:         66  common_preempt_count:          0
+    { len:        116 } hitcount:         81  common_preempt_count:         40
+    { len:        708 } hitcount:        112  common_preempt_count:          0
+    { len:         46 } hitcount:        221  common_preempt_count:          0
+    { len:       1264 } hitcount:        458  common_preempt_count:          0
+
+    Totals:
+        Hits: 1428
+        Entries: 147
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+    #
+
+    { skbaddr: ffff8800baee5e00 } hitcount:          1  len:        130
+    { skbaddr: ffff88005f3d5600 } hitcount:          1  len:       1280
+    { skbaddr: ffff88005f3d4900 } hitcount:          1  len:       1280
+    { skbaddr: ffff88009fed6300 } hitcount:          1  len:        115
+    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:        115
+    { skbaddr: ffff88008cdb1900 } hitcount:          1  len:         46
+    { skbaddr: ffff880064b5ef00 } hitcount:          1  len:        118
+    { skbaddr: ffff880044e3c700 } hitcount:          1  len:         60
+    { skbaddr: ffff880100065900 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d46bd500 } hitcount:          1  len:        116
+    { skbaddr: ffff88005f3d5f00 } hitcount:          1  len:       1280
+    { skbaddr: ffff880100064700 } hitcount:          1  len:        365
+    { skbaddr: ffff8800badb6f00 } hitcount:          1  len:         60
+    .
+    .
+    .
+    { skbaddr: ffff88009fe0be00 } hitcount:         27  len:      24677
+    { skbaddr: ffff88009fe0a400 } hitcount:         27  len:      23052
+    { skbaddr: ffff88009fe0b700 } hitcount:         31  len:      25589
+    { skbaddr: ffff88009fe0b600 } hitcount:         32  len:      27326
+    { skbaddr: ffff88006a462800 } hitcount:         68  len:      71678
+    { skbaddr: ffff88006a463700 } hitcount:         70  len:      72678
+    { skbaddr: ffff88006a462b00 } hitcount:         71  len:      77589
+    { skbaddr: ffff88006a463600 } hitcount:         73  len:      71307
+    { skbaddr: ffff88006a462200 } hitcount:         81  len:      81032
+
+    Totals:
+        Hits: 1451
+        Entries: 318
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len == 256 [active]
+    #
+
+
+    Totals:
+        Hits: 0
+        Entries: 0
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len > 4096 [active]
+    #
+
+    { skbaddr: ffff88009fd2c300 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcce00 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcd700 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcda00 } hitcount:          1  len:      21492
+    { skbaddr: ffff8800ae2e2d00 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcdb00 } hitcount:          1  len:       7212
+    { skbaddr: ffff88006a4df500 } hitcount:          1  len:       4854
+    { skbaddr: ffff88008ce47b00 } hitcount:          1  len:      18636
+    { skbaddr: ffff8800ae2e2200 } hitcount:          1  len:      12924
+    { skbaddr: ffff88005f3e1000 } hitcount:          1  len:       4356
+    { skbaddr: ffff8800d2bcdc00 } hitcount:          2  len:      24420
+    { skbaddr: ffff8800d2bcc200 } hitcount:          2  len:      12996
+
+    Totals:
+        Hits: 14
+        Entries: 12
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len < 0 [active]
+    #
+
+
+    Totals:
+        Hits: 0
+        Entries: 0
+        Dropped: 0
+
+  Named triggers can be used to have triggers share a common set of
+  histogram data.  This capability is mostly useful for combining the
+  output of events generated by tracepoints contained inside inline
+  functions, but names can be used in a hist trigger on any event.
+  For example, these two triggers when hit will update the same 'len'
+  field in the shared 'foo' histogram data:
+
+    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
+           /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  You can see that they're updating common histogram data by reading
+  each event's hist files at the same time:
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
+      cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+    # event histogram
+    #
+    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+    #
+
+    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
+    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
+    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
+    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
+    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
+    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
+    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
+    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
+    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
+    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
+    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
+    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
+    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
+    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
+    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
+    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
+    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
+    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
+    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
+    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
+    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
+    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
+    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
+    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
+    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
+    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
+    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
+    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
+    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
+    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
+    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
+    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
+    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
+    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
+    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
+    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
+    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
+
+    Totals:
+        Hits: 81
+        Entries: 42
+        Dropped: 0
+    # event histogram
+    #
+    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+    #
+
+    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
+    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
+    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
+    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
+    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
+    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
+    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
+    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
+    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
+    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
+    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
+    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
+    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
+    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
+    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
+    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
+    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
+    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
+    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
+    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
+    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
+    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
+    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
+    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
+    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
+    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
+    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
+    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
+    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
+    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
+    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
+    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
+    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
+    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
+    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
+    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
+    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
+
+    Totals:
+        Hits: 81
+        Entries: 42
+        Dropped: 0
+
+  And here's an example that shows how to combine histogram data from
+  any two events even if they don't share any 'compatible' fields
+  other than 'hitcount' and 'stacktrace'.  These commands create a
+  couple of triggers named 'bar' using those fields:
+
+    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
+          /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  And displaying the output of either shows some interesting if
+  somewhat confusing output:
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+    # event histogram
+    #
+    # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active]
+    #
+
+    { stacktrace:
+             _do_fork+0x18e/0x330
+             kernel_thread+0x29/0x30
+             kthreadd+0x154/0x1b0
+             ret_from_fork+0x3f/0x70
+    } hitcount:          1
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx_ni+0x20/0x70
+             dev_loopback_xmit+0xaa/0xd0
+             ip_mc_output+0x126/0x240
+             ip_local_out_sk+0x31/0x40
+             igmp_send_report+0x1e9/0x230
+             igmp_timer_expire+0xe9/0x120
+             call_timer_fn+0x39/0xf0
+             run_timer_softirq+0x1e1/0x290
+             __do_softirq+0xfd/0x290
+             irq_exit+0x98/0xb0
+             smp_apic_timer_interrupt+0x4a/0x60
+             apic_timer_interrupt+0x6d/0x80
+             cpuidle_enter+0x17/0x20
+             call_cpuidle+0x3b/0x60
+             cpu_startup_entry+0x22d/0x310
+    } hitcount:          1
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx_ni+0x20/0x70
+             dev_loopback_xmit+0xaa/0xd0
+             ip_mc_output+0x17f/0x240
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x13e/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             SYSC_sendto+0xef/0x170
+             SyS_sendto+0xe/0x10
+             entry_SYSCALL_64_fastpath+0x12/0x6a
+    } hitcount:          2
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx+0x1c/0x60
+             loopback_xmit+0x6c/0xb0
+             dev_hard_start_xmit+0x219/0x3a0
+             __dev_queue_xmit+0x415/0x4f0
+             dev_queue_xmit_sk+0x13/0x20
+             ip_finish_output2+0x237/0x340
+             ip_finish_output+0x113/0x1d0
+             ip_output+0x66/0xc0
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x16d/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             ___sys_sendmsg+0x14e/0x270
+    } hitcount:         76
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx+0x1c/0x60
+             loopback_xmit+0x6c/0xb0
+             dev_hard_start_xmit+0x219/0x3a0
+             __dev_queue_xmit+0x415/0x4f0
+             dev_queue_xmit_sk+0x13/0x20
+             ip_finish_output2+0x237/0x340
+             ip_finish_output+0x113/0x1d0
+             ip_output+0x66/0xc0
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x16d/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             ___sys_sendmsg+0x269/0x270
+    } hitcount:         77
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx+0x1c/0x60
+             loopback_xmit+0x6c/0xb0
+             dev_hard_start_xmit+0x219/0x3a0
+             __dev_queue_xmit+0x415/0x4f0
+             dev_queue_xmit_sk+0x13/0x20
+             ip_finish_output2+0x237/0x340
+             ip_finish_output+0x113/0x1d0
+             ip_output+0x66/0xc0
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x16d/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             SYSC_sendto+0xef/0x170
+    } hitcount:         88
+    { stacktrace:
+             _do_fork+0x18e/0x330
+             SyS_clone+0x19/0x20
+             entry_SYSCALL_64_fastpath+0x12/0x6a
+    } hitcount:        244
+
+    Totals:
+        Hits: 489
+        Entries: 7
+        Dropped: 0
+
+
+2.2 Inter-event hist triggers
+-----------------------------
+
+Inter-event hist triggers are hist triggers that combine values from
+one or more other events and create a histogram using that data.  Data
+from an inter-event histogram can in turn become the source for
+further combined histograms, thus providing a chain of related
+histograms, which is important for some applications.
+
+The most important example of an inter-event quantity that can be used
+in this manner is latency, which is simply a difference in timestamps
+between two events.  Although latency is the most important
+inter-event quantity, note that because the support is completely
+general across the trace event subsystem, any event field can be used
+in an inter-event quantity.
+
+An example of a histogram that combines data from other histograms
+into a useful chain would be a 'wakeupswitch latency' histogram that
+combines a 'wakeup latency' histogram and a 'switch latency'
+histogram.
+
+Normally, a hist trigger specification consists of a (possibly
+compound) key along with one or more numeric values, which are
+continually updated sums associated with that key.  A histogram
+specification in this case consists of individual key and value
+specifications that refer to trace event fields associated with a
+single event type.
+
+The inter-event hist trigger extension allows fields from multiple
+events to be referenced and combined into a multi-event histogram
+specification.  In support of this overall goal, a few enabling
+features have been added to the hist trigger support:
+
+  - In order to compute an inter-event quantity, a value from one
+    event needs to saved and then referenced from another event.  This
+    requires the introduction of support for histogram 'variables'.
+
+  - The computation of inter-event quantities and their combination
+    require some minimal amount of support for applying simple
+    expressions to variables (+ and -).
+
+  - A histogram consisting of inter-event quantities isn't logically a
+    histogram on either event (so having the 'hist' file for either
+    event host the histogram output doesn't really make sense).  To
+    address the idea that the histogram is associated with a
+    combination of events, support is added allowing the creation of
+    'synthetic' events that are events derived from other events.
+    These synthetic events are full-fledged events just like any other
+    and can be used as such, as for instance to create the
+    'combination' histograms mentioned previously.
+
+  - A set of 'actions' can be associated with histogram entries -
+    these can be used to generate the previously mentioned synthetic
+    events, but can also be used for other purposes, such as for
+    example saving context when a 'max' latency has been hit.
+
+  - Trace events don't have a 'timestamp' associated with them, but
+    there is an implicit timestamp saved along with an event in the
+    underlying ftrace ring buffer.  This timestamp is now exposed as a
+    a synthetic field named 'common_timestamp' which can be used in
+    histograms as if it were any other event field; it isn't an actual
+    field in the trace format but rather is a synthesized value that
+    nonetheless can be used as if it were an actual field.  By default
+    it is in units of nanoseconds; appending '.usecs' to a
+    common_timestamp field changes the units to microseconds.
+
+A note on inter-event timestamps: If common_timestamp is used in a
+histogram, the trace buffer is automatically switched over to using
+absolute timestamps and the "global" trace clock, in order to avoid
+bogus timestamp differences with other clocks that aren't coherent
+across CPUs.  This can be overridden by specifying one of the other
+trace clocks instead, using the "clock=XXX" hist trigger attribute,
+where XXX is any of the clocks listed in the tracing/trace_clock
+pseudo-file.
+
+These features are described in more detail in the following sections.
+
+2.2.1 Histogram Variables
+-------------------------
+
+Variables are simply named locations used for saving and retrieving
+values between matching events.  A 'matching' event is defined as an
+event that has a matching key - if a variable is saved for a histogram
+entry corresponding to that key, any subsequent event with a matching
+key can access that variable.
+
+A variable's value is normally available to any subsequent event until
+it is set to something else by a subsequent event.  The one exception
+to that rule is that any variable used in an expression is essentially
+'read-once' - once it's used by an expression in a subsequent event,
+it's reset to its 'unset' state, which means it can't be used again
+unless it's set again.  This ensures not only that an event doesn't
+use an uninitialized variable in a calculation, but that that variable
+is used only once and not for any unrelated subsequent match.
+
+The basic syntax for saving a variable is to simply prefix a unique
+variable name not corresponding to any keyword along with an '=' sign
+to any event field.
+
+Either keys or values can be saved and retrieved in this way.  This
+creates a variable named 'ts0' for a histogram entry with the key
+'next_pid':
+
+  # echo 'hist:keys=next_pid:vals=$ts0:ts0=common_timestamp ... >> \
+       event/trigger
+
+The ts0 variable can be accessed by any subsequent event having the
+same pid as 'next_pid'.
+
+Variable references are formed by prepending the variable name with
+the '$' sign.  Thus for example, the ts0 variable above would be
+referenced as '$ts0' in expressions.
+
+Because 'vals=' is used, the common_timestamp variable value above
+will also be summed as a normal histogram value would (though for a
+timestamp it makes little sense).
+
+The below shows that a key value can also be saved in the same way:
+
+  # echo 'hist:timer_pid=common_pid:key=timer_pid ...' >> event/trigger
+
+If a variable isn't a key variable or prefixed with 'vals=', the
+associated event field will be saved in a variable but won't be summed
+as a value:
+
+  # echo 'hist:keys=next_pid:ts1=common_timestamp ... >> event/trigger
+
+Multiple variables can be assigned at the same time.  The below would
+result in both ts0 and b being created as variables, with both
+common_timestamp and field1 additionally being summed as values:
+
+  # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ... >> \
+       event/trigger
+
+Note that variable assignments can appear either preceding or
+following their use.  The command below behaves identically to the
+command above:
+
+  # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ... >> \
+       event/trigger
+
+Any number of variables not bound to a 'vals=' prefix can also be
+assigned by simply separating them with colons.  Below is the same
+thing but without the values being summed in the histogram:
+
+  # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ... >> event/trigger
+
+Variables set as above can be referenced and used in expressions on
+another event.
+
+For example, here's how a latency can be calculated:
+
+  # echo 'hist:keys=pid,prio:ts0=common_timestamp ... >> event1/trigger
+  # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ... >> event2/trigger
+
+In the first line above, the event's timetamp is saved into the
+variable ts0.  In the next line, ts0 is subtracted from the second
+event's timestamp to produce the latency, which is then assigned into
+yet another variable, 'wakeup_lat'.  The hist trigger below in turn
+makes use of the wakeup_lat variable to compute a combined latency
+using the same key and variable from yet another event:
+
+  # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ... >> event3/trigger
+
+2.2.2 Synthetic Events
+----------------------
+
+Synthetic events are user-defined events generated from hist trigger
+variables or fields associated with one or more other events.  Their
+purpose is to provide a mechanism for displaying data spanning
+multiple events consistent with the existing and already familiar
+usage for normal events.
+
+To define a synthetic event, the user writes a simple specification
+consisting of the name of the new event along with one or more
+variables and their types, which can be any valid field type,
+separated by semicolons, to the tracing/synthetic_events file.
+
+For instance, the following creates a new event named 'wakeup_latency'
+with 3 fields: lat, pid, and prio.  Each of those fields is simply a
+variable reference to a variable on another event:
+
+  # echo 'wakeup_latency \
+          u64 lat; \
+          pid_t pid; \
+         int prio' >> \
+         /sys/kernel/debug/tracing/synthetic_events
+
+Reading the tracing/synthetic_events file lists all the currently
+defined synthetic events, in this case the event defined above:
+
+  # cat /sys/kernel/debug/tracing/synthetic_events
+    wakeup_latency u64 lat; pid_t pid; int prio
+
+An existing synthetic event definition can be removed by prepending
+the command that defined it with a '!':
+
+  # echo '!wakeup_latency u64 lat pid_t pid int prio' >> \
+    /sys/kernel/debug/tracing/synthetic_events
+
+At this point, there isn't yet an actual 'wakeup_latency' event
+instantiated in the event subsytem - for this to happen, a 'hist
+trigger action' needs to be instantiated and bound to actual fields
+and variables defined on other events (see Section 6.3.3 below).
+
+Once that is done, an event instance is created, and a histogram can
+be defined using it:
+
+  # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
+        /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+
+The new event is created under the tracing/events/synthetic/ directory
+and looks and behaves just like any other event:
+
+  # ls /sys/kernel/debug/tracing/events/synthetic/wakeup_latency
+        enable  filter  format  hist  id  trigger
+
+Like any other event, once a histogram is enabled for the event, the
+output can be displayed by reading the event's 'hist' file.
+
+2.2.3 Hist trigger 'actions'
+----------------------------
+
+A hist trigger 'action' is a function that's executed whenever a
+histogram entry is added or updated.
+
+The default 'action' if no special function is explicity specified is
+as it always has been, to simply update the set of values associated
+with an entry.  Some applications, however, may want to perform
+additional actions at that point, such as generate another event, or
+compare and save a maximum.
+
+The following additional actions are available.  To specify an action
+for a given event, simply specify the action between colons in the
+hist trigger specification.
+
+  - onmatch(matching.event).<synthetic_event_name>(param list)
+
+    The 'onmatch(matching.event).<synthetic_event_name>(params)' hist
+    trigger action is invoked whenever an event matches and the
+    histogram entry would be added or updated.  It causes the named
+    synthetic event to be generated with the values given in the
+    'param list'.  The result is the generation of a synthetic event
+    that consists of the values contained in those variables at the
+    time the invoking event was hit.
+
+    The 'param list' consists of one or more parameters which may be
+    either variables or fields defined on either the 'matching.event'
+    or the target event.  The variables or fields specified in the
+    param list may be either fully-qualified or unqualified.  If a
+    variable is specified as unqualified, it must be unique between
+    the two events.  A field name used as a param can be unqualified
+    if it refers to the target event, but must be fully qualified if
+    it refers to the matching event.  A fully-qualified name is of the
+    form 'system.event_name.$var_name' or 'system.event_name.field'.
+
+    The 'matching.event' specification is simply the fully qualified
+    event name of the event that matches the target event for the
+    onmatch() functionality, in the form 'system.event_name'.
+
+    Finally, the number and type of variables/fields in the 'param
+    list' must match the number and types of the fields in the
+    synthetic event being generated.
+
+    As an example the below defines a simple synthetic event and uses
+    a variable defined on the sched_wakeup_new event as a parameter
+    when invoking the synthetic event.  Here we define the synthetic
+    event:
+
+    # echo 'wakeup_new_test pid_t pid' >> \
+           /sys/kernel/debug/tracing/synthetic_events
+
+    # cat /sys/kernel/debug/tracing/synthetic_events
+          wakeup_new_test pid_t pid
+
+    The following hist trigger both defines the missing testpid
+    variable and specifies an onmatch() action that generates a
+    wakeup_new_test synthetic event whenever a sched_wakeup_new event
+    occurs, which because of the 'if comm == "cyclictest"' filter only
+    happens when the executable is cyclictest:
+
+    # echo 'hist:keys=$testpid:testpid=pid:onmatch(sched.sched_wakeup_new).\
+            wakeup_new_test($testpid) if comm=="cyclictest"' >> \
+            /sys/kernel/debug/tracing/events/sched/sched_wakeup_new/trigger
+
+    Creating and displaying a histogram based on those events is now
+    just a matter of using the fields and new synthetic event in the
+    tracing/events/synthetic directory, as usual:
+
+    # echo 'hist:keys=pid:sort=pid' >> \
+           /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/trigger
+
+    Running 'cyclictest' should cause wakeup_new events to generate
+    wakeup_new_test synthetic events which should result in histogram
+    output in the wakeup_new_test event's hist file:
+
+    # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/hist
+
+    A more typical usage would be to use two events to calculate a
+    latency.  The following example uses a set of hist triggers to
+    produce a 'wakeup_latency' histogram:
+
+    First, we define a 'wakeup_latency' synthetic event:
+
+    # echo 'wakeup_latency u64 lat; pid_t pid; int prio' >> \
+            /sys/kernel/debug/tracing/synthetic_events
+
+    Next, we specify that whenever we see a sched_waking event for a
+    cyclictest thread, save the timestamp in a 'ts0' variable:
+
+    # echo 'hist:keys=$saved_pid:saved_pid=pid:ts0=common_timestamp.usecs \
+            if comm=="cyclictest"' >> \
+           /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+
+    Then, when the corresponding thread is actually scheduled onto the
+    CPU by a sched_switch event, calculate the latency and use that
+    along with another variable and an event field to generate a
+    wakeup_latency synthetic event:
+
+    # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:\
+            onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,\
+                   $saved_pid,next_prio) if next_comm=="cyclictest"' >> \
+           /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+
+    We also need to create a histogram on the wakeup_latency synthetic
+    event in order to aggregate the generated synthetic event data:
+
+    # echo 'hist:keys=pid,prio,lat:sort=pid,lat' >> \
+            /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+
+    Finally, once we've run cyclictest to actually generate some
+    events, we can see the output by looking at the wakeup_latency
+    synthetic event's hist file:
+
+    # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/hist
+
+  - onmax(var).save(field,..   .)
+
+    The 'onmax(var).save(field,...)' hist trigger action is invoked
+    whenever the value of 'var' associated with a histogram entry
+    exceeds the current maximum contained in that variable.
+
+    The end result is that the trace event fields specified as the
+    onmax.save() params will be saved if 'var' exceeds the current
+    maximum for that hist trigger entry.  This allows context from the
+    event that exhibited the new maximum to be saved for later
+    reference.  When the histogram is displayed, additional fields
+    displaying the saved values will be printed.
+
+    As an example the below defines a couple of hist triggers, one for
+    sched_waking and another for sched_switch, keyed on pid.  Whenever
+    a sched_waking occurs, the timestamp is saved in the entry
+    corresponding to the current pid, and when the scheduler switches
+    back to that pid, the timestamp difference is calculated.  If the
+    resulting latency, stored in wakeup_lat, exceeds the current
+    maximum latency, the values specified in the save() fields are
+    recoreded:
+
+    # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
+            if comm=="cyclictest"' >> \
+            /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+
+    # echo 'hist:keys=next_pid:\
+            wakeup_lat=common_timestamp.usecs-$ts0:\
+            onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) \
+            if next_comm=="cyclictest"' >> \
+            /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+
+    When the histogram is displayed, the max value and the saved
+    values corresponding to the max are displayed following the rest
+    of the fields:
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist
+      { next_pid:       2255 } hitcount:        239
+        common_timestamp-ts0:          0
+        max:         27
+       next_comm: cyclictest
+        prev_pid:          0  prev_prio:        120  prev_comm: swapper/1
+
+      { next_pid:       2256 } hitcount:       2355
+        common_timestamp-ts0: 0
+        max:         49  next_comm: cyclictest
+        prev_pid:          0  prev_prio:        120  prev_comm: swapper/0
+
+      Totals:
+          Hits: 12970
+          Entries: 2
+          Dropped: 0
diff --git a/arch/Kconfig b/arch/Kconfig
index 40dc31fea90c..7c6108479209 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -20,6 +20,7 @@ config OPROFILE
        tristate "OProfile system profiling"
        depends on PROFILING
        depends on HAVE_OPROFILE
+       depends on !PREEMPT_RT_FULL
        select RING_BUFFER
        select RING_BUFFER_ALLOW_SWAP
        help
diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h
index 1d5716bc060b..6883bc952d22 100644
--- a/arch/alpha/include/asm/spinlock_types.h
+++ b/arch/alpha/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ALPHA_SPINLOCK_TYPES_H
 #define _ALPHA_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d1346a160760..558b0995e94a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -45,7 +45,7 @@ config ARM
        select HARDIRQS_SW_RESEND
        select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
        select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-       select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+       select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT_BASE
        select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
        select HAVE_ARCH_MMAP_RND_BITS if MMU
        select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
@@ -85,6 +85,7 @@ config ARM
        select HAVE_PERF_EVENTS
        select HAVE_PERF_REGS
        select HAVE_PERF_USER_STACK_DUMP
+       select HAVE_PREEMPT_LAZY
        select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
        select HAVE_REGS_AND_STACK_ACCESS_API
        select HAVE_SYSCALL_TRACEPOINTS
@@ -2164,7 +2165,7 @@ config NEON
 
 config KERNEL_MODE_NEON
        bool "Support for NEON in kernel mode"
-       depends on NEON && AEABI
+       depends on NEON && AEABI && !PREEMPT_RT_BASE
        help
          Say Y to include support for NEON in kernel mode.
 
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index b6f319606e30..ad377ef73739 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -23,6 +23,8 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
 struct irqaction;
 struct pt_regs;
 extern void migrate_irqs(void);
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
index 5976958647fe..a37c0803954b 100644
--- a/arch/arm/include/asm/spinlock_types.h
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 #define TICKET_SHIFT   16
 
 typedef struct {
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index d3e937dcee4d..6ab96a2ce1f8 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -4,6 +4,13 @@
 
 #include <linux/thread_info.h>
 
+#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p);
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
 /*
  * For v7 SMP cores running a preemptible kernel we may be pre-empted
  * during a TLB maintenance operation, so execute an inner-shareable dsb
@@ -26,6 +33,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 #define switch_to(prev,next,last)                                      \
 do {                                                                   \
        __complete_pending_tlbi();                                      \
+       switch_kmaps(prev, next);                                       \
        last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));        \
 } while (0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 57d2ad9c75ca..cdfb6855943b 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -49,6 +49,7 @@ struct cpu_context_save {
 struct thread_info {
        unsigned long           flags;          /* low level flags */
        int                     preempt_count;  /* 0 => preemptable, <0 => bug */
+       int                     preempt_lazy_count; /* 0 => preemptable, <0 => bug */
        mm_segment_t            addr_limit;     /* address limit */
        struct task_struct      *task;          /* main task structure */
        __u32                   cpu;            /* cpu */
@@ -142,7 +143,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define TIF_SYSCALL_TRACE      4       /* syscall trace active */
 #define TIF_SYSCALL_AUDIT      5       /* syscall auditing active */
 #define TIF_SYSCALL_TRACEPOINT 6       /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP            7       /* seccomp syscall filtering active */
+#define TIF_SECCOMP            8       /* seccomp syscall filtering active */
+#define TIF_NEED_RESCHED_LAZY  7
 
 #define TIF_NOHZ               12      /* in adaptive nohz mode */
 #define TIF_USING_IWMMXT       17
@@ -152,6 +154,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define _TIF_SIGPENDING                (1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED      (1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME     (1 << TIF_NOTIFY_RESUME)
+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_UPROBE            (1 << TIF_UPROBE)
 #define _TIF_SYSCALL_TRACE     (1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT     (1 << TIF_SYSCALL_AUDIT)
@@ -167,7 +170,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK         (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-                                _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+                                _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+                                _TIF_NEED_RESCHED_LAZY)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 608008229c7d..3866da3f7bb7 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -65,6 +65,7 @@ int main(void)
   BLANK();
   DEFINE(TI_FLAGS,             offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,           offsetof(struct thread_info, preempt_count));
+  DEFINE(TI_PREEMPT_LAZY,      offsetof(struct thread_info, preempt_lazy_count));
   DEFINE(TI_ADDR_LIMIT,                offsetof(struct thread_info, addr_limit));
   DEFINE(TI_TASK,              offsetof(struct thread_info, task));
   DEFINE(TI_CPU,               offsetof(struct thread_info, cpu));
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index fbc707626b3e..b434c59d2b64 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -220,11 +220,18 @@ __irq_svc:
 
 #ifdef CONFIG_PREEMPT
        ldr     r8, [tsk, #TI_PREEMPT]          @ get preempt count
-       ldr     r0, [tsk, #TI_FLAGS]            @ get flags
        teq     r8, #0                          @ if preempt count != 0
+       bne     1f                              @ return from exeption
+       ldr     r0, [tsk, #TI_FLAGS]            @ get flags
+       tst     r0, #_TIF_NEED_RESCHED          @ if NEED_RESCHED is set
+       blne    svc_preempt                     @ preempt!
+
+       ldr     r8, [tsk, #TI_PREEMPT_LAZY]     @ get preempt lazy count
+       teq     r8, #0                          @ if preempt lazy count != 0
        movne   r0, #0                          @ force flags to 0
-       tst     r0, #_TIF_NEED_RESCHED
+       tst     r0, #_TIF_NEED_RESCHED_LAZY
        blne    svc_preempt
+1:
 #endif
 
        svc_exit r5, irq = 1                    @ return from exception
@@ -239,8 +246,14 @@ svc_preempt:
 1:     bl      preempt_schedule_irq            @ irq en/disable is done inside
        ldr     r0, [tsk, #TI_FLAGS]            @ get new tasks TI_FLAGS
        tst     r0, #_TIF_NEED_RESCHED
+       bne     1b
+       tst     r0, #_TIF_NEED_RESCHED_LAZY
        reteq   r8                              @ go again
-       b       1b
+       ldr     r0, [tsk, #TI_PREEMPT_LAZY]     @ get preempt lazy count
+       teq     r0, #0                          @ if preempt lazy count != 0
+       beq     1b
+       ret     r8                              @ go again
+
 #endif
 
 __und_fault:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 54c10503d71f..3fdeade24e3f 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -53,7 +53,9 @@ ret_fast_syscall:
        cmp     r2, #TASK_SIZE
        blne    addr_limit_check_failed
        ldr     r1, [tsk, #TI_FLAGS]            @ re-check for syscall tracing
-       tst     r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+       tst     r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
+       bne     fast_work_pending
+       tst     r1, #_TIF_SECCOMP
        bne     fast_work_pending
 
 
@@ -83,8 +85,11 @@ ret_fast_syscall:
        cmp     r2, #TASK_SIZE
        blne    addr_limit_check_failed
        ldr     r1, [tsk, #TI_FLAGS]            @ re-check for syscall tracing
-       tst     r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+       tst     r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
+       bne     do_slower_path
+       tst     r1, #_TIF_SECCOMP
        beq     no_work_pending
+do_slower_path:
  UNWIND(.fnend         )
 ENDPROC(ret_fast_syscall)
 
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index a50dc00d79a2..d0a05a3bdb96 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,7 +16,7 @@ struct patch {
        unsigned int insn;
 };
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
        __acquires(&patch_lock)
@@ -33,7 +33,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
                return addr;
 
        if (flags)
-               spin_lock_irqsave(&patch_lock, *flags);
+               raw_spin_lock_irqsave(&patch_lock, *flags);
        else
                __acquire(&patch_lock);
 
@@ -48,7 +48,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
        clear_fixmap(fixmap);
 
        if (flags)
-               spin_unlock_irqrestore(&patch_lock, *flags);
+               raw_spin_unlock_irqrestore(&patch_lock, *flags);
        else
                __release(&patch_lock);
 }
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d96714e1858c..cf4e1452d4b4 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -325,6 +325,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 }
 
 #ifdef CONFIG_MMU
+/*
+ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock.  If the lock is not
+ * initialized by pgtable_page_ctor() then a coredump of the vector page will
+ * fail.
+ */
+static int __init vectors_user_mapping_init_page(void)
+{
+       struct page *page;
+       unsigned long addr = 0xffff0000;
+       pgd_t *pgd;
+       pud_t *pud;
+       pmd_t *pmd;
+
+       pgd = pgd_offset_k(addr);
+       pud = pud_offset(pgd, addr);
+       pmd = pmd_offset(pud, addr);
+       page = pmd_page(*(pmd));
+
+       pgtable_page_ctor(page);
+
+       return 0;
+}
+late_initcall(vectors_user_mapping_init_page);
+
 #ifdef CONFIG_KUSER_HELPERS
 /*
  * The vectors page is always readable from user space for the
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index cdfe52b15a0a..198cf8bf0b37 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -615,7 +615,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
         */
        trace_hardirqs_off();
        do {
-               if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+               if (likely(thread_flags & (_TIF_NEED_RESCHED |
+                                          _TIF_NEED_RESCHED_LAZY))) {
                        schedule();
                } else {
                        if (unlikely(!user_mode(regs)))
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index e61af0600133..d8f2e77d5651 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -237,8 +237,6 @@ int __cpu_disable(void)
        flush_cache_louis();
        local_flush_tlb_all();
 
-       clear_tasks_mm_cpumask(cpu);
-
        return 0;
 }
 
@@ -256,6 +254,7 @@ void __cpu_die(unsigned int cpu)
        }
        pr_debug("CPU%u: shutdown\n", cpu);
 
+       clear_tasks_mm_cpumask(cpu);
        /*
         * platform_cpu_kill() is generally expected to do the powering off
         * and/or cutting of clocks to the dying CPU.  Optionally, this may
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 0bee233fef9a..314cfb232a63 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
 static const struct unwind_idx *__origin_unwind_idx;
 extern const struct unwind_idx __stop_unwind_idx[];
 
-static DEFINE_SPINLOCK(unwind_lock);
+static DEFINE_RAW_SPINLOCK(unwind_lock);
 static LIST_HEAD(unwind_tables);
 
 /* Convert a prel31 symbol to an absolute address */
@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
                /* module unwind tables */
                struct unwind_table *table;
 
-               spin_lock_irqsave(&unwind_lock, flags);
+               raw_spin_lock_irqsave(&unwind_lock, flags);
                list_for_each_entry(table, &unwind_tables, list) {
                        if (addr >= table->begin_addr &&
                            addr < table->end_addr) {
@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
                                break;
                        }
                }
-               spin_unlock_irqrestore(&unwind_lock, flags);
+               raw_spin_unlock_irqrestore(&unwind_lock, flags);
        }
 
        pr_debug("%s: idx = %p\n", __func__, idx);
@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
        tab->begin_addr = text_addr;
        tab->end_addr = text_addr + text_size;
 
-       spin_lock_irqsave(&unwind_lock, flags);
+       raw_spin_lock_irqsave(&unwind_lock, flags);
        list_add_tail(&tab->list, &unwind_tables);
-       spin_unlock_irqrestore(&unwind_lock, flags);
+       raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
        return tab;
 }
@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_table *tab)
        if (!tab)
                return;
 
-       spin_lock_irqsave(&unwind_lock, flags);
+       raw_spin_lock_irqsave(&unwind_lock, flags);
        list_del(&tab->list);
-       spin_unlock_irqrestore(&unwind_lock, flags);
+       raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
        kfree(tab);
 }
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 5a03bffe7226..3080ea833d19 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -229,7 +229,7 @@ static void __iomem *scu_base_addr(void)
        return (void __iomem *)(S5P_VA_SCU);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void exynos_secondary_init(unsigned int cpu)
 {
@@ -242,8 +242,8 @@ static void exynos_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr)
@@ -307,7 +307,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * Set synchronisation state between this boot processor
         * and the secondary one
         */
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * The secondary processor is waiting to be released from
@@ -334,7 +334,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
                if (timeout == 0) {
                        printk(KERN_ERR "cpu1 power enable failed");
-                       spin_unlock(&boot_lock);
+                       raw_spin_unlock(&boot_lock);
                        return -ETIMEDOUT;
                }
        }
@@ -380,7 +380,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * calibrations, then wait for it to finish
         */
 fail:
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return pen_release != -1 ? ret : 0;
 }
diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c
index f66815c3dd07..00524abd963f 100644
--- a/arch/arm/mach-hisi/platmcpm.c
+++ b/arch/arm/mach-hisi/platmcpm.c
@@ -61,7 +61,7 @@
 
 static void __iomem *sysctrl, *fabric;
 static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 static u32 fabric_phys_addr;
 /*
  * [0]: bootwrapper physical address
@@ -113,7 +113,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle)
        if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER)
                return -EINVAL;
 
-       spin_lock_irq(&boot_lock);
+       raw_spin_lock_irq(&boot_lock);
 
        if (hip04_cpu_table[cluster][cpu])
                goto out;
@@ -147,7 +147,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle)
 
 out:
        hip04_cpu_table[cluster][cpu]++;
-       spin_unlock_irq(&boot_lock);
+       raw_spin_unlock_irq(&boot_lock);
 
        return 0;
 }
@@ -162,11 +162,11 @@ static void hip04_cpu_die(unsigned int l_cpu)
        cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
        cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
        hip04_cpu_table[cluster][cpu]--;
        if (hip04_cpu_table[cluster][cpu] == 1) {
                /* A power_up request went ahead of us. */
-               spin_unlock(&boot_lock);
+               raw_spin_unlock(&boot_lock);
                return;
        } else if (hip04_cpu_table[cluster][cpu] > 1) {
                pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
@@ -174,7 +174,7 @@ static void hip04_cpu_die(unsigned int l_cpu)
        }
 
        last_man = hip04_cluster_is_down(cluster);
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
        if (last_man) {
                /* Since it's Cortex A15, disable L2 prefetching. */
                asm volatile(
@@ -203,7 +203,7 @@ static int hip04_cpu_kill(unsigned int l_cpu)
               cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
 
        count = TIMEOUT_MSEC / POLL_MSEC;
-       spin_lock_irq(&boot_lock);
+       raw_spin_lock_irq(&boot_lock);
        for (tries = 0; tries < count; tries++) {
                if (hip04_cpu_table[cluster][cpu])
                        goto err;
@@ -211,10 +211,10 @@ static int hip04_cpu_kill(unsigned int l_cpu)
                data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
                if (data & CORE_WFI_STATUS(cpu))
                        break;
-               spin_unlock_irq(&boot_lock);
+               raw_spin_unlock_irq(&boot_lock);
                /* Wait for clean L2 when the whole cluster is down. */
                msleep(POLL_MSEC);
-               spin_lock_irq(&boot_lock);
+               raw_spin_lock_irq(&boot_lock);
        }
        if (tries >= count)
                goto err;
@@ -231,10 +231,10 @@ static int hip04_cpu_kill(unsigned int l_cpu)
                goto err;
        if (hip04_cluster_is_down(cluster))
                hip04_set_snoop_filter(cluster, 0);
-       spin_unlock_irq(&boot_lock);
+       raw_spin_unlock_irq(&boot_lock);
        return 1;
 err:
-       spin_unlock_irq(&boot_lock);
+       raw_spin_unlock_irq(&boot_lock);
        return 0;
 }
 #endif
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 1c73694c871a..ac4d2f030b87 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -69,7 +69,7 @@ static const struct omap_smp_config omap5_cfg __initconst = {
        .startup_addr = omap5_secondary_startup,
 };
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void __iomem *omap4_get_scu_base(void)
 {
@@ -177,8 +177,8 @@ static void omap4_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -191,7 +191,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * Set synchronisation state between this boot processor
         * and the secondary one
         */
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * Update the AuxCoreBoot0 with boot state for secondary core.
@@ -270,7 +270,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * Now the secondary core is starting up let it run its
         * calibrations, then wait for it to finish
         */
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return 0;
 }
diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c
index 75ef5d4be554..c17c86e5d860 100644
--- a/arch/arm/mach-prima2/platsmp.c
+++ b/arch/arm/mach-prima2/platsmp.c
@@ -22,7 +22,7 @@
 
 static void __iomem *clk_base;
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void sirfsoc_secondary_init(unsigned int cpu)
 {
@@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 static const struct of_device_id clk_ids[]  = {
@@ -75,7 +75,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
        /* make sure write buffer is drained */
        mb();
 
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * The secondary processor is waiting to be released from
@@ -107,7 +107,7 @@ static int sirfsoc_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * now the secondary core is starting up let it run its
         * calibrations, then wait for it to finish
         */
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return pen_release != -1 ? -ENOSYS : 0;
 }
diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c
index 5494c9e0c909..e8ce157d3548 100644
--- a/arch/arm/mach-qcom/platsmp.c
+++ b/arch/arm/mach-qcom/platsmp.c
@@ -46,7 +46,7 @@
 
 extern void secondary_startup_arm(void);
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
 static void qcom_cpu_die(unsigned int cpu)
@@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 static int scss_release_secondary(unsigned int cpu)
@@ -284,7 +284,7 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int))
         * set synchronisation state between this boot processor
         * and the secondary one
         */
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * Send the secondary CPU a soft interrupt, thereby causing
@@ -297,7 +297,7 @@ static int qcom_boot_secondary(unsigned int cpu, int (*func)(unsigned int))
         * now the secondary core is starting up let it run its
         * calibrations, then wait for it to finish
         */
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return ret;
 }
diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
index 39038a03836a..6da5c93872bf 100644
--- a/arch/arm/mach-spear/platsmp.c
+++ b/arch/arm/mach-spear/platsmp.c
@@ -32,7 +32,7 @@ static void write_pen_release(int val)
        sync_cache_w(&pen_release);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void __iomem *scu_base = IOMEM(VA_SCU_BASE);
 
@@ -47,8 +47,8 @@ static void spear13xx_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -59,7 +59,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * set synchronisation state between this boot processor
         * and the secondary one
         */
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * The secondary processor is waiting to be released from
@@ -84,7 +84,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * now the secondary core is starting up let it run its
         * calibrations, then wait for it to finish
         */
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return pen_release != -1 ? -ENOSYS : 0;
 }
diff --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c
index 231f19e17436..a3419b7003e6 100644
--- a/arch/arm/mach-sti/platsmp.c
+++ b/arch/arm/mach-sti/platsmp.c
@@ -35,7 +35,7 @@ static void write_pen_release(int val)
        sync_cache_w(&pen_release);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void sti_secondary_init(unsigned int cpu)
 {
@@ -48,8 +48,8 @@ static void sti_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -60,7 +60,7 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * set synchronisation state between this boot processor
         * and the secondary one
         */
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * The secondary processor is waiting to be released from
@@ -91,7 +91,7 @@ static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * now the secondary core is starting up let it run its
         * calibrations, then wait for it to finish
         */
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return pen_release != -1 ? -ENOSYS : 0;
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 49b1b8048635..b261967ea028 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -437,6 +437,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
        if (addr < TASK_SIZE)
                return do_page_fault(addr, fsr, regs);
 
+       if (interrupts_enabled(regs))
+               local_irq_enable();
+
        if (user_mode(regs))
                goto bad_area;
 
@@ -504,6 +507,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
+       if (interrupts_enabled(regs))
+               local_irq_enable();
+
        do_bad_area(addr, fsr, regs);
        return 0;
 }
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index d02f8187b1cc..542692dbd40a 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
        return *ptep;
 }
 
+static unsigned int fixmap_idx(int type)
+{
+       return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+}
+
 void *kmap(struct page *page)
 {
        might_sleep();
@@ -54,12 +59,13 @@ EXPORT_SYMBOL(kunmap);
 
 void *kmap_atomic(struct page *page)
 {
+       pte_t pte = mk_pte(page, kmap_prot);
        unsigned int idx;
        unsigned long vaddr;
        void *kmap;
        int type;
 
-       preempt_disable();
+       preempt_disable_nort();
        pagefault_disable();
        if (!PageHighMem(page))
                return page_address(page);
@@ -79,7 +85,7 @@ void *kmap_atomic(struct page *page)
 
        type = kmap_atomic_idx_push();
 
-       idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+       idx = fixmap_idx(type);
        vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
        /*
@@ -93,7 +99,10 @@ void *kmap_atomic(struct page *page)
         * in place, so the contained TLB flush ensures the TLB is updated
         * with the new mapping.
         */
-       set_fixmap_pte(idx, mk_pte(page, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+       current->kmap_pte[type] = pte;
+#endif
+       set_fixmap_pte(idx, pte);
 
        return (void *)vaddr;
 }
@@ -106,44 +115,75 @@ void __kunmap_atomic(void *kvaddr)
 
        if (kvaddr >= (void *)FIXADDR_START) {
                type = kmap_atomic_idx();
-               idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+               idx = fixmap_idx(type);
 
                if (cache_is_vivt())
                        __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
+#ifdef CONFIG_PREEMPT_RT_FULL
+               current->kmap_pte[type] = __pte(0);
+#endif
 #ifdef CONFIG_DEBUG_HIGHMEM
                BUG_ON(vaddr != __fix_to_virt(idx));
-               set_fixmap_pte(idx, __pte(0));
 #else
                (void) idx;  /* to kill a warning */
 #endif
+               set_fixmap_pte(idx, __pte(0));
                kmap_atomic_idx_pop();
        } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
                /* this address was obtained through kmap_high_get() */
                kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
        }
        pagefault_enable();
-       preempt_enable();
+       preempt_enable_nort();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
 void *kmap_atomic_pfn(unsigned long pfn)
 {
+       pte_t pte = pfn_pte(pfn, kmap_prot);
        unsigned long vaddr;
        int idx, type;
        struct page *page = pfn_to_page(pfn);
 
-       preempt_disable();
+       preempt_disable_nort();
        pagefault_disable();
        if (!PageHighMem(page))
                return page_address(page);
 
        type = kmap_atomic_idx_push();
-       idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+       idx = fixmap_idx(type);
        vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
        BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
 #endif
-       set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+       current->kmap_pte[type] = pte;
+#endif
+       set_fixmap_pte(idx, pte);
 
        return (void *)vaddr;
 }
+#if defined CONFIG_PREEMPT_RT_FULL
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+       int i;
+
+       /*
+        * Clear @prev's kmap_atomic mappings
+        */
+       for (i = 0; i < prev_p->kmap_idx; i++) {
+               int idx = fixmap_idx(i);
+
+               set_fixmap_pte(idx, __pte(0));
+       }
+       /*
+        * Restore @next_p's kmap_atomic mappings
+        */
+       for (i = 0; i < next_p->kmap_idx; i++) {
+               int idx = fixmap_idx(i);
+
+               if (!pte_none(next_p->kmap_pte[i]))
+                       set_fixmap_pte(idx, next_p->kmap_pte[i]);
+       }
+}
+#endif
diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
index c2366510187a..6b60f582b738 100644
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -32,7 +32,7 @@ static void write_pen_release(int val)
        sync_cache_w(&pen_release);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void versatile_secondary_init(unsigned int cpu)
 {
@@ -45,8 +45,8 @@ void versatile_secondary_init(unsigned int cpu)
        /*
         * Synchronise with the boot thread.
         */
-       spin_lock(&boot_lock);
-       spin_unlock(&boot_lock);
+       raw_spin_lock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 }
 
 int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -57,7 +57,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * Set synchronisation state between this boot processor
         * and the secondary one
         */
-       spin_lock(&boot_lock);
+       raw_spin_lock(&boot_lock);
 
        /*
         * This is really belt and braces; we hold unintended secondary
@@ -87,7 +87,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
         * now the secondary core is starting up let it run its
         * calibrations, then wait for it to finish
         */
-       spin_unlock(&boot_lock);
+       raw_spin_unlock(&boot_lock);
 
        return pen_release != -1 ? -ENOSYS : 0;
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c30cd78b6918..458d2033ffde 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -103,6 +103,7 @@ config ARM64
        select HAVE_PERF_EVENTS
        select HAVE_PERF_REGS
        select HAVE_PERF_USER_STACK_DUMP
+       select HAVE_PREEMPT_LAZY
        select HAVE_REGS_AND_STACK_ACCESS_API
        select HAVE_RCU_TABLE_FREE
        select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 70c517aa4501..2a5f05b5a19a 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -19,19 +19,19 @@ config CRYPTO_SHA512_ARM64
 
 config CRYPTO_SHA1_ARM64_CE
        tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_HASH
        select CRYPTO_SHA1
 
 config CRYPTO_SHA2_ARM64_CE
        tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_HASH
        select CRYPTO_SHA256_ARM64
 
 config CRYPTO_GHASH_ARM64_CE
        tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_HASH
        select CRYPTO_GF128MUL
        select CRYPTO_AES
@@ -39,7 +39,7 @@ config CRYPTO_GHASH_ARM64_CE
 
 config CRYPTO_CRCT10DIF_ARM64_CE
        tristate "CRCT10DIF digest algorithm using PMULL instructions"
-       depends on KERNEL_MODE_NEON && CRC_T10DIF
+       depends on KERNEL_MODE_NEON && CRC_T10DIF && !PREEMPT_RT_BASE
        select CRYPTO_HASH
 
 config CRYPTO_CRC32_ARM64_CE
@@ -53,13 +53,13 @@ config CRYPTO_AES_ARM64
 
 config CRYPTO_AES_ARM64_CE
        tristate "AES core cipher using ARMv8 Crypto Extensions"
-       depends on ARM64 && KERNEL_MODE_NEON
+       depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_ALGAPI
        select CRYPTO_AES_ARM64
 
 config CRYPTO_AES_ARM64_CE_CCM
        tristate "AES in CCM mode using ARMv8 Crypto Extensions"
-       depends on ARM64 && KERNEL_MODE_NEON
+       depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_ALGAPI
        select CRYPTO_AES_ARM64_CE
        select CRYPTO_AES_ARM64
@@ -67,7 +67,7 @@ config CRYPTO_AES_ARM64_CE_CCM
 
 config CRYPTO_AES_ARM64_CE_BLK
        tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_BLKCIPHER
        select CRYPTO_AES_ARM64_CE
        select CRYPTO_AES_ARM64
@@ -75,7 +75,7 @@ config CRYPTO_AES_ARM64_CE_BLK
 
 config CRYPTO_AES_ARM64_NEON_BLK
        tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_BLKCIPHER
        select CRYPTO_AES_ARM64
        select CRYPTO_AES
@@ -83,13 +83,13 @@ config CRYPTO_AES_ARM64_NEON_BLK
 
 config CRYPTO_CHACHA20_NEON
        tristate "NEON accelerated ChaCha20 symmetric cipher"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_BLKCIPHER
        select CRYPTO_CHACHA20
 
 config CRYPTO_AES_ARM64_BS
        tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm"
-       depends on KERNEL_MODE_NEON
+       depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE
        select CRYPTO_BLKCIPHER
        select CRYPTO_AES_ARM64_NEON_BLK
        select CRYPTO_AES_ARM64
diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c
index 34b4e3d46aab..ae055cdad8cf 100644
--- a/arch/arm64/crypto/crc32-ce-glue.c
+++ b/arch/arm64/crypto/crc32-ce-glue.c
@@ -208,7 +208,8 @@ static struct shash_alg crc32_pmull_algs[] = { {
 
 static int __init crc32_pmull_mod_init(void)
 {
-       if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) {
+       if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+           !IS_ENABLED(CONFIG_PREEMPT_RT_BASE) && (elf_hwcap & HWCAP_PMULL)) {
                crc32_pmull_algs[0].update = crc32_pmull_update;
                crc32_pmull_algs[1].update = crc32c_pmull_update;
 
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 55be59a35e3f..ba0cf1361f65 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -16,10 +16,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H)
-# error "please don't include this file directly"
-#endif
-
 #include <linux/types.h>
 
 #define TICKET_SHIFT   16
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index fc786d344e46..b833258b7594 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -43,6 +43,7 @@ struct thread_info {
        u64                     ttbr0;          /* saved TTBR0_EL1 */
 #endif
        int                     preempt_count;  /* 0 => preemptable, <0 => bug */
+       int                     preempt_lazy_count; /* 0 => preemptable, <0 => bug */
 };
 
 #define INIT_THREAD_INFO(tsk)                                          \
@@ -82,6 +83,7 @@ void arch_setup_new_exec(void);
 #define TIF_FOREIGN_FPSTATE    3       /* CPU's FP state is not current's */
 #define TIF_UPROBE             4       /* uprobe breakpoint or singlestep */
 #define TIF_FSCHECK            5       /* Check FS is USER_DS on return */
+#define TIF_NEED_RESCHED_LAZY  6
 #define TIF_NOHZ               7
 #define TIF_SYSCALL_TRACE      8
 #define TIF_SYSCALL_AUDIT      9
@@ -98,6 +100,7 @@ void arch_setup_new_exec(void);
 #define _TIF_NEED_RESCHED      (1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME     (1 << TIF_NOTIFY_RESUME)
 #define _TIF_FOREIGN_FPSTATE   (1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOHZ              (1 << TIF_NOHZ)
 #define _TIF_SYSCALL_TRACE     (1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT     (1 << TIF_SYSCALL_AUDIT)
@@ -109,8 +112,9 @@ void arch_setup_new_exec(void);
 
 #define _TIF_WORK_MASK         (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
                                 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-                                _TIF_UPROBE | _TIF_FSCHECK)
+                                _TIF_UPROBE | _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY)
 
+#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 #define _TIF_SYSCALL_WORK      (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
                                 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
                                 _TIF_NOHZ)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index b5e43b01b396..ae26a1664436 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -39,6 +39,7 @@ int main(void)
   BLANK();
   DEFINE(TSK_TI_FLAGS,         offsetof(struct task_struct, thread_info.flags));
   DEFINE(TSK_TI_PREEMPT,       offsetof(struct task_struct, thread_info.preempt_count));
+  DEFINE(TSK_TI_PREEMPT_LAZY,  offsetof(struct task_struct, thread_info.preempt_lazy_count));
   DEFINE(TSK_TI_ADDR_LIMIT,    offsetof(struct task_struct, thread_info.addr_limit));
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
   DEFINE(TSK_TI_TTBR0,         offsetof(struct task_struct, thread_info.ttbr0));
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c1ffa95c0ad2..c60ecb5a3916 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -637,11 +637,16 @@ el1_irq:
 
 #ifdef CONFIG_PREEMPT
        ldr     w24, [tsk, #TSK_TI_PREEMPT]     // get preempt count
-       cbnz    w24, 1f                         // preempt count != 0
+       cbnz    w24, 2f                         // preempt count != 0
        ldr     x0, [tsk, #TSK_TI_FLAGS]        // get flags
-       tbz     x0, #TIF_NEED_RESCHED, 1f       // needs rescheduling?
-       bl      el1_preempt
+       tbnz    x0, #TIF_NEED_RESCHED, 1f       // needs rescheduling?
+
+       ldr     w24, [tsk, #TSK_TI_PREEMPT_LAZY] // get preempt lazy count
+       cbnz    w24, 2f                         // preempt lazy count != 0
+       tbz     x0, #TIF_NEED_RESCHED_LAZY, 2f  // needs rescheduling?
 1:
+       bl      el1_preempt
+2:
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
        bl      trace_hardirqs_on
@@ -655,6 +660,7 @@ el1_preempt:
 1:     bl      preempt_schedule_irq            // irq en/disable is done inside
        ldr     x0, [tsk, #TSK_TI_FLAGS]        // get new tasks TI_FLAGS
        tbnz    x0, #TIF_NEED_RESCHED, 1b       // needs rescheduling?
+       tbnz    x0, #TIF_NEED_RESCHED_LAZY, 1b  // needs rescheduling?
        ret     x24
 #endif
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 43442b3a463f..81bf9545a589 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -756,7 +756,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
                /* Check valid user FS if needed */
                addr_limit_user_check();
 
-               if (thread_flags & _TIF_NEED_RESCHED) {
+               if (thread_flags & _TIF_NEED_RESCHED_MASK) {
                        schedule();
                } else {
                        local_irq_enable();
diff --git a/arch/blackfin/include/asm/spinlock_types.h b/arch/blackfin/include/asm/spinlock_types.h
index 1a33608c958b..103b34d3dcf6 100644
--- a/arch/blackfin/include/asm/spinlock_types.h
+++ b/arch/blackfin/include/asm/spinlock_types.h
@@ -7,10 +7,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 #include <asm/rwlock.h>
 
 typedef struct {
diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h
index 7a906b5214a4..d8f596fec022 100644
--- a/arch/hexagon/include/asm/spinlock_types.h
+++ b/arch/hexagon/include/asm/spinlock_types.h
@@ -21,10 +21,6 @@
 #ifndef _ASM_SPINLOCK_TYPES_H
 #define _ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h
index 6e345fefcdca..681408d6816f 100644
--- a/arch/ia64/include/asm/spinlock_types.h
+++ b/arch/ia64/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_IA64_SPINLOCK_TYPES_H
 #define _ASM_IA64_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 555b11180156..6866201a7603 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1824,7 +1824,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
        ti->cpu = cpu;
        p->stack = ti;
        p->state = TASK_UNINTERRUPTIBLE;
-       cpumask_set_cpu(cpu, &p->cpus_allowed);
+       cpumask_set_cpu(cpu, &p->cpus_mask);
        INIT_LIST_HEAD(&p->tasks);
        p->parent = p->real_parent = p->group_leader = p;
        INIT_LIST_HEAD(&p->children);
diff --git a/arch/m32r/include/asm/spinlock_types.h b/arch/m32r/include/asm/spinlock_types.h
index bb0d17b64198..fc6afa42fe11 100644
--- a/arch/m32r/include/asm/spinlock_types.h
+++ b/arch/m32r/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_M32R_SPINLOCK_TYPES_H
 #define _ASM_M32R_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile int slock;
 } arch_spinlock_t;
diff --git a/arch/metag/include/asm/spinlock_types.h b/arch/metag/include/asm/spinlock_types.h
index cd197f1bed59..adc26e9797c5 100644
--- a/arch/metag/include/asm/spinlock_types.h
+++ b/arch/metag/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_METAG_SPINLOCK_TYPES_H
 #define _ASM_METAG_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c82457b0e733..7bb1838508de 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2519,7 +2519,7 @@ config MIPS_ASID_BITS_VARIABLE
 #
 config HIGHMEM
        bool "High Memory Support"
-       depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA
+       depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL
 
 config CPU_SUPPORTS_HIGHMEM
        bool
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index e610473d61b8..1428b4febbc9 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -42,7 +42,7 @@ extern struct task_struct *ll_task;
  * inline to try to keep the overhead down. If we have been forced to run on
  * a "CPU" with an FPU because of a previous high level of FP computation,
  * but did not actually use the FPU during the most recent time-slice (CU1
- * isn't set), we undo the restriction on cpus_allowed.
+ * isn't set), we undo the restriction on cpus_mask.
  *
  * We're not calling set_cpus_allowed() here, because we have no need to
  * force prompt migration - we're already switching the current CPU to a
@@ -57,7 +57,7 @@ do {                                                                  \
            test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) &&             \
            (!(KSTK_STATUS(prev) & ST0_CU1))) {                         \
                clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND);          \
-               prev->cpus_allowed = prev->thread.user_cpus_allowed;    \
+               prev->cpus_mask = prev->thread.user_cpus_allowed;       \
        }                                                               \
        next->thread.emulated_fp = 0;                                   \
 } while(0)
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index a7c0f97e4b0d..1a08428eedcf 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
        if (retval)
                goto out_unlock;
 
-       cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+       cpumask_or(&allowed, &p->thread.user_cpus_allowed, p->cpus_ptr);
        cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 583aed906933..24ad7aaca5eb 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1193,12 +1193,12 @@ static void mt_ase_fp_affinity(void)
                 * restricted the allowed set to exclude any CPUs with FPUs,
                 * we'll skip the procedure.
                 */
-               if (cpumask_intersects(&current->cpus_allowed, &mt_fpu_cpumask)) {
+               if (cpumask_intersects(&current->cpus_mask, &mt_fpu_cpumask)) {
                        cpumask_t tmask;
 
                        current->thread.user_cpus_allowed
-                               = current->cpus_allowed;
-                       cpumask_and(&tmask, &current->cpus_allowed,
+                               = current->cpus_mask;
+                       cpumask_and(&tmask, &current->cpus_mask,
                                    &mt_fpu_cpumask);
                        set_cpus_allowed_ptr(current, &tmask);
                        set_thread_flag(TIF_FPUBOUND);
diff --git a/arch/mn10300/include/asm/spinlock_types.h b/arch/mn10300/include/asm/spinlock_types.h
index 32abdc89bbc7..c45230a12d60 100644
--- a/arch/mn10300/include/asm/spinlock_types.h
+++ b/arch/mn10300/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_SPINLOCK_TYPES_H
 #define _ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct arch_spinlock {
        unsigned int slock;
 } arch_spinlock_t;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fe418226df7f..b5658e925465 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -111,10 +111,11 @@ config LOCKDEP_SUPPORT
 
 config RWSEM_GENERIC_SPINLOCK
        bool
+       default y if PREEMPT_RT_FULL
 
 config RWSEM_XCHGADD_ALGORITHM
        bool
-       default y
+       default y if !PREEMPT_RT_FULL
 
 config GENERIC_LOCKBREAK
        bool
@@ -215,6 +216,7 @@ config PPC
        select HAVE_HARDLOCKUP_DETECTOR_PERF    if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
        select HAVE_PERF_REGS
        select HAVE_PERF_USER_STACK_DUMP
+       select HAVE_PREEMPT_LAZY
        select HAVE_RCU_TABLE_FREE              if SMP
        select HAVE_REGS_AND_STACK_ACCESS_API
        select HAVE_SYSCALL_TRACEPOINTS
@@ -390,7 +392,7 @@ menu "Kernel options"
 
 config HIGHMEM
        bool "High memory support"
-       depends on PPC32
+       depends on PPC32 && !PREEMPT_RT_FULL
 
 source kernel/Kconfig.hz
 source kernel/Kconfig.preempt
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 87adaf13b7e8..7305cb6a53e4 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H
 #define _ASM_POWERPC_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int slock;
 } arch_spinlock_t;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index a264c3ad366b..020afb8329a1 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -36,6 +36,8 @@ struct thread_info {
        int             cpu;                    /* cpu we're on */
        int             preempt_count;          /* 0 => preemptable,
                                                   <0 => BUG */
+       int             preempt_lazy_count;     /* 0 => preemptable,
+                                                  <0 => BUG */
        unsigned long   local_flags;            /* private flags for thread */
 #ifdef CONFIG_LIVEPATCH
        unsigned long *livepatch_sp;
@@ -81,8 +83,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_TRACE      0       /* syscall trace active */
 #define TIF_SIGPENDING         1       /* signal pending */
 #define TIF_NEED_RESCHED       2       /* rescheduling necessary */
-#define TIF_POLLING_NRFLAG     3       /* true if poll_idle() is polling
-                                          TIF_NEED_RESCHED */
+#define TIF_NEED_RESCHED_LAZY  3       /* lazy rescheduling necessary */
 #define TIF_32BIT              4       /* 32 bit binary */
 #define TIF_RESTORE_TM         5       /* need to restore TM FP/VEC/VSX */
 #define TIF_PATCH_PENDING      6       /* pending live patching update */
@@ -101,6 +102,8 @@ static inline struct thread_info *current_thread_info(void)
 #if defined(CONFIG_PPC64)
 #define TIF_ELF2ABI            18      /* function descriptors must die! */
 #endif
+#define TIF_POLLING_NRFLAG     19      /* true if poll_idle() is polling
+                                          TIF_NEED_RESCHED */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE     (1<<TIF_SYSCALL_TRACE)
@@ -120,14 +123,16 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_TRACEPOINT        (1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE       (1<<TIF_EMULATE_STACK_STORE)
 #define _TIF_NOHZ              (1<<TIF_NOHZ)
+#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY)
 #define _TIF_SYSCALL_DOTRACE   (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
                                 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
                                 _TIF_NOHZ)
 
 #define _TIF_USER_WORK_MASK    (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
                                 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-                                _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
+                                _TIF_RESTORE_TM | _TIF_PATCH_PENDING | _TIF_NEED_RESCHED_LAZY)
 #define _TIF_PERSYSCALL_MASK   (_TIF_RESTOREALL|_TIF_NOERROR)
+#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 
 /* Bits in local_flags */
 /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2e5ea300258a..a2cb40098d7c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -156,6 +156,7 @@ int main(void)
        OFFSET(TI_FLAGS, thread_info, flags);
        OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
        OFFSET(TI_PREEMPT, thread_info, preempt_count);
+       OFFSET(TI_PREEMPT_LAZY, thread_info, preempt_lazy_count);
        OFFSET(TI_TASK, thread_info, task);
        OFFSET(TI_CPU, thread_info, cpu);
 
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e780e1fbf6c2..dc7fe90ff6a9 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -866,7 +866,14 @@ resume_kernel:
        cmpwi   0,r0,0          /* if non-zero, just restore regs and return */
        bne     restore
        andi.   r8,r8,_TIF_NEED_RESCHED
+       bne+    1f
+       lwz     r0,TI_PREEMPT_LAZY(r9)
+       cmpwi   0,r0,0          /* if non-zero, just restore regs and return */
+       bne     restore
+       lwz     r0,TI_FLAGS(r9)
+       andi.   r0,r0,_TIF_NEED_RESCHED_LAZY
        beq+    restore
+1:
        lwz     r3,_MSR(r1)
        andi.   r0,r3,MSR_EE    /* interrupts off? */
        beq     restore         /* don't schedule if so */
@@ -877,11 +884,11 @@ resume_kernel:
         */
        bl      trace_hardirqs_off
 #endif
-1:     bl      preempt_schedule_irq
+2:     bl      preempt_schedule_irq
        CURRENT_THREAD_INFO(r9, r1)
        lwz     r3,TI_FLAGS(r9)
-       andi.   r0,r3,_TIF_NEED_RESCHED
-       bne-    1b
+       andi.   r0,r3,_TIF_NEED_RESCHED_MASK
+       bne-    2b
 #ifdef CONFIG_TRACE_IRQFLAGS
        /* And now, to properly rebalance the above, we tell lockdep they
         * are being turned back on, which will happen when we return
@@ -1204,7 +1211,7 @@ global_dbcr0:
 #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
 
 do_work:                       /* r10 contains MSR_KERNEL here */
-       andi.   r0,r9,_TIF_NEED_RESCHED
+       andi.   r0,r9,_TIF_NEED_RESCHED_MASK
        beq     do_user_signal
 
 do_resched:                    /* r10 contains MSR_KERNEL here */
@@ -1225,7 +1232,7 @@ recheck:
        MTMSRD(r10)             /* disable interrupts */
        CURRENT_THREAD_INFO(r9, r1)
        lwz     r9,TI_FLAGS(r9)
-       andi.   r0,r9,_TIF_NEED_RESCHED
+       andi.   r0,r9,_TIF_NEED_RESCHED_MASK
        bne-    do_resched
        andi.   r0,r9,_TIF_USER_WORK_MASK
        beq     restore_user
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index c194f4c8e66b..117c1f6cab66 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -690,7 +690,7 @@ _GLOBAL(ret_from_except_lite)
        bl      restore_math
        b       restore
 #endif
-1:     andi.   r0,r4,_TIF_NEED_RESCHED
+1:     andi.   r0,r4,_TIF_NEED_RESCHED_MASK
        beq     2f
        bl      restore_interrupts
        SCHEDULE_USER
@@ -752,10 +752,18 @@ resume_kernel:
 
 #ifdef CONFIG_PREEMPT
        /* Check if we need to preempt */
+       lwz     r8,TI_PREEMPT(r9)
+       cmpwi   0,r8,0          /* if non-zero, just restore regs and return */
+       bne     restore
        andi.   r0,r4,_TIF_NEED_RESCHED
+       bne+    check_count
+
+       andi.   r0,r4,_TIF_NEED_RESCHED_LAZY
        beq+    restore
+       lwz     r8,TI_PREEMPT_LAZY(r9)
+
        /* Check that preempt_count() == 0 and interrupts are enabled */
-       lwz     r8,TI_PREEMPT(r9)
+check_count:
        cmpwi   cr1,r8,0
        ld      r0,SOFTE(r1)
        cmpdi   r0,0
@@ -772,7 +780,7 @@ resume_kernel:
        /* Re-test flags and eventually loop */
        CURRENT_THREAD_INFO(r9, r1)
        ld      r4,TI_FLAGS(r9)
-       andi.   r0,r4,_TIF_NEED_RESCHED
+       andi.   r0,r4,_TIF_NEED_RESCHED_MASK
        bne     1b
 
        /*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0ce8b0e5d7ba..375adb3048fc 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -693,6 +693,7 @@ void irq_ctx_init(void)
        }
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
        struct thread_info *curtp, *irqtp;
@@ -710,6 +711,7 @@ void do_softirq_own_stack(void)
        if (irqtp->flags)
                set_bits(irqtp->flags, &curtp->flags);
 }
+#endif
 
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 3f7a9a2d2435..1795359d27b6 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -41,6 +41,7 @@
  * We store the saved ksp_limit in the unused part
  * of the STACK_FRAME_OVERHEAD
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
        mflr    r0
        stw     r0,4(r1)
@@ -57,6 +58,7 @@ _GLOBAL(call_do_softirq)
        stw     r10,THREAD+KSP_LIMIT(r2)
        mtlr    r0
        blr
+#endif
 
 /*
  * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 3280953a82cf..dd2a80d190c4 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -31,6 +31,7 @@
 
        .text
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
        mflr    r0
        std     r0,16(r1)
@@ -41,6 +42,7 @@ _GLOBAL(call_do_softirq)
        ld      r0,16(r1)
        mtlr    r0
        blr
+#endif
 
 _GLOBAL(call_do_irq)
        mflr    r0
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 648160334abf..9d24331fc9b4 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -177,6 +177,7 @@ config KVM_E500MC
 config KVM_MPIC
        bool "KVM in-kernel MPIC emulation"
        depends on KVM && E500
+       depends on !PREEMPT_RT_FULL
        select HAVE_KVM_IRQCHIP
        select HAVE_KVM_IRQFD
        select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 1fbb5da17dd2..ca86366d5424 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_context *ctx)
         * runqueue. The context will be rescheduled on the proper node
         * if it is timesliced or preempted.
         */
-       cpumask_copy(&ctx->cpus_allowed, &current->cpus_allowed);
+       cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr);
 
        /* Save the current cpu id for spu interrupt routing. */
        ctx->last_ran = raw_smp_processor_id();
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e48462447ff0..2670cee66064 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -752,7 +752,7 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
        }
        pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);
 
-       res = wait_event_interruptible(dev->done.wait,
+       res = swait_event_interruptible(dev->done.wait,
                                       dev->done.done || kthread_should_stop());
        if (kthread_should_stop())
                res = -EINTR;
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index 1861a0c5dd47..74092ebaca3c 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        int lock;
 } __attribute__ ((aligned (4))) arch_spinlock_t;
diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h
index e82369f286a2..22ca9a98bbb8 100644
--- a/arch/sh/include/asm/spinlock_types.h
+++ b/arch/sh/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SH_SPINLOCK_TYPES_H
 #define __ASM_SH_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 245dbeb20afe..e298c82d2a69 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -148,6 +148,7 @@ void irq_ctx_exit(int cpu)
        hardirq_ctx[cpu] = NULL;
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
        struct thread_info *curctx;
@@ -175,6 +176,7 @@ void do_softirq_own_stack(void)
                  "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
        );
 }
+#endif
 #else
 static inline void handle_one_irq(unsigned int irq)
 {
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 4e83f950713e..7f9d71523763 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -206,12 +206,10 @@ config NR_CPUS
 source kernel/Kconfig.hz
 
 config RWSEM_GENERIC_SPINLOCK
-       bool
-       default y if SPARC32
+       def_bool PREEMPT_RT_FULL
 
 config RWSEM_XCHGADD_ALGORITHM
-       bool
-       default y if SPARC64
+       def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
 
 config GENERIC_HWEIGHT
        bool
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d66dde833f5e..f87b3f8f4d43 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -855,6 +855,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
        set_irq_regs(old_regs);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
        void *orig_sp, *sp = softirq_stack[smp_processor_id()];
@@ -869,6 +870,7 @@ void do_softirq_own_stack(void)
        __asm__ __volatile__("mov %0, %%sp"
                             : : "r" (orig_sp));
 }
+#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(void)
diff --git a/arch/tile/include/asm/setup.h b/arch/tile/include/asm/setup.h
index 2a0347af0702..670fa2f4cfc3 100644
--- a/arch/tile/include/asm/setup.h
+++ b/arch/tile/include/asm/setup.h
@@ -49,7 +49,7 @@ int hardwall_ipi_valid(int cpu);
 
 /* Hook hardwall code into changes in affinity. */
 #define arch_set_cpus_allowed(p, new_mask) do { \
-       if (!cpumask_equal(&p->cpus_allowed, new_mask)) \
+       if (!cpumask_equal(p->cpus_ptr, new_mask)) \
                hardwall_deactivate_all(p); \
 } while (0)
 #endif
diff --git a/arch/tile/include/asm/spinlock_types.h b/arch/tile/include/asm/spinlock_types.h
index a71f59b49c50..9311c6ff2abc 100644
--- a/arch/tile/include/asm/spinlock_types.h
+++ b/arch/tile/include/asm/spinlock_types.h
@@ -15,10 +15,6 @@
 #ifndef _ASM_TILE_SPINLOCK_TYPES_H
 #define _ASM_TILE_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 #ifdef __tilegx__
 
 /* Low 15 bits are "next"; high 15 bits are "current". */
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 2fd1694ac1d0..98f4fb696289 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -590,12 +590,12 @@ static int hardwall_activate(struct hardwall_info *info)
         * Get our affinity; if we're not bound to this tile uniquely,
         * we can't access the network registers.
         */
-       if (cpumask_weight(&p->cpus_allowed) != 1)
+       if (p->nr_cpus_allowed != 1)
                return -EPERM;
 
        /* Make sure we are bound to a cpu assigned to this resource. */
        cpu = smp_processor_id();
-       BUG_ON(cpumask_first(&p->cpus_allowed) != cpu);
+       BUG_ON(cpumask_first(p->cpus_ptr) != cpu);
        if (!cpumask_test_cpu(cpu, &info->cpumask))
                return -EINVAL;
 
@@ -621,17 +621,17 @@ static int hardwall_activate(struct hardwall_info *info)
  * Deactivate a task's hardwall.  Must hold lock for hardwall_type.
  * This method may be called from exit_thread(), so we don't want to
  * rely on too many fields of struct task_struct still being valid.
- * We assume the cpus_allowed, pid, and comm fields are still valid.
+ * We assume the nr_cpus_allowed, pid, and comm fields are still valid.
  */
 static void _hardwall_deactivate(struct hardwall_type *hwt,
                                 struct task_struct *task)
 {
        struct thread_struct *ts = &task->thread;
 
-       if (cpumask_weight(&task->cpus_allowed) != 1) {
+       if (task->nr_cpus_allowed != 1) {
                pr_err("pid %d (%s) releasing %s hardwall with an affinity mask containing %d cpus!\n",
                       task->pid, task->comm, hwt->name,
-                      cpumask_weight(&task->cpus_allowed));
+                      task->nr_cpus_allowed);
                BUG();
        }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2af0af33362a..7764f936d6ab 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -169,6 +169,7 @@ config X86
        select HAVE_HARDLOCKUP_DETECTOR_PERF    if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
        select HAVE_PERF_REGS
        select HAVE_PERF_USER_STACK_DUMP
+       select HAVE_PREEMPT_LAZY
        select HAVE_RCU_TABLE_FREE
        select HAVE_RCU_TABLE_INVALIDATE        if HAVE_RCU_TABLE_FREE
        select HAVE_REGS_AND_STACK_ACCESS_API
@@ -257,8 +258,11 @@ config ARCH_MAY_HAVE_PC_FDC
        def_bool y
        depends on ISA_DMA_API
 
+config RWSEM_GENERIC_SPINLOCK
+       def_bool PREEMPT_RT_FULL
+
 config RWSEM_XCHGADD_ALGORITHM
-       def_bool y
+       def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
 
 config GENERIC_CALIBRATE_DELAY
        def_bool y
@@ -933,7 +937,7 @@ config IOMMU_HELPER
 config MAXSMP
        bool "Enable Maximum number of SMP Processors and NUMA Nodes"
        depends on X86_64 && SMP && DEBUG_KERNEL
-       select CPUMASK_OFFSTACK
+       select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL
        ---help---
          Enable maximum number of CPUS and NUMA Nodes for this architecture.
          If unsure, say N.
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index c690ddc78c03..7a3138d33e33 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -387,14 +387,14 @@ static int ecb_encrypt(struct skcipher_request *req)
 
        err = skcipher_walk_virt(&walk, req, true);
 
-       kernel_fpu_begin();
        while ((nbytes = walk.nbytes)) {
+               kernel_fpu_begin();
                aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
                              nbytes & AES_BLOCK_MASK);
+               kernel_fpu_end();
                nbytes &= AES_BLOCK_SIZE - 1;
                err = skcipher_walk_done(&walk, nbytes);
        }
-       kernel_fpu_end();
 
        return err;
 }
@@ -409,14 +409,14 @@ static int ecb_decrypt(struct skcipher_request *req)
 
        err = skcipher_walk_virt(&walk, req, true);
 
-       kernel_fpu_begin();
        while ((nbytes = walk.nbytes)) {
+               kernel_fpu_begin();
                aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
                              nbytes & AES_BLOCK_MASK);
+               kernel_fpu_end();
                nbytes &= AES_BLOCK_SIZE - 1;
                err = skcipher_walk_done(&walk, nbytes);
        }
-       kernel_fpu_end();
 
        return err;
 }
@@ -431,14 +431,14 @@ static int cbc_encrypt(struct skcipher_request *req)
 
        err = skcipher_walk_virt(&walk, req, true);
 
-       kernel_fpu_begin();
        while ((nbytes = walk.nbytes)) {
+               kernel_fpu_begin();
                aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
                              nbytes & AES_BLOCK_MASK, walk.iv);
+               kernel_fpu_end();
                nbytes &= AES_BLOCK_SIZE - 1;
                err = skcipher_walk_done(&walk, nbytes);
        }
-       kernel_fpu_end();
 
        return err;
 }
@@ -453,14 +453,14 @@ static int cbc_decrypt(struct skcipher_request *req)
 
        err = skcipher_walk_virt(&walk, req, true);
 
-       kernel_fpu_begin();
        while ((nbytes = walk.nbytes)) {
+               kernel_fpu_begin();
                aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
                              nbytes & AES_BLOCK_MASK, walk.iv);
+               kernel_fpu_end();
                nbytes &= AES_BLOCK_SIZE - 1;
                err = skcipher_walk_done(&walk, nbytes);
        }
-       kernel_fpu_end();
 
        return err;
 }
@@ -510,18 +510,20 @@ static int ctr_crypt(struct skcipher_request *req)
 
        err = skcipher_walk_virt(&walk, req, true);
 
-       kernel_fpu_begin();
        while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+               kernel_fpu_begin();
                aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
                                      nbytes & AES_BLOCK_MASK, walk.iv);
+               kernel_fpu_end();
                nbytes &= AES_BLOCK_SIZE - 1;
                err = skcipher_walk_done(&walk, nbytes);
        }
        if (walk.nbytes) {
+               kernel_fpu_begin();
                ctr_crypt_final(ctx, &walk);
+               kernel_fpu_end();
                err = skcipher_walk_done(&walk, 0);
        }
-       kernel_fpu_end();
 
        return err;
 }
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 60907c139c4e..0902db7d326a 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -206,6 +206,20 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void camellia_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       camellia_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+#else
+static void camellia_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
@@ -221,16 +235,19 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        }
 
        if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
                nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
        }
 
        while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
                nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
        }
+       camellia_fpu_end_rt(ctx);
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                camellia_enc_blk(ctx->ctx, srcdst, srcdst);
@@ -251,16 +268,19 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        }
 
        if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
                nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
        }
 
        while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
                nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
        }
+       camellia_fpu_end_rt(ctx);
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                camellia_dec_blk(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index d96429da88eb..3b8e91841039 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -210,6 +210,21 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void camellia_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       camellia_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void camellia_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
@@ -225,10 +240,12 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        }
 
        while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
                nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
        }
+       camellia_fpu_end_rt(ctx);
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                camellia_enc_blk(ctx->ctx, srcdst, srcdst);
@@ -249,10 +266,12 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        }
 
        while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
                nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
        }
+       camellia_fpu_end_rt(ctx);
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                camellia_dec_blk(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 575292a33bdf..0a4b0a222b18 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -59,7 +59,7 @@ static inline void cast5_fpu_end(bool fpu_enabled)
 static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
                     bool enc)
 {
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
        const unsigned int bsize = CAST5_BLOCK_SIZE;
        unsigned int nbytes;
@@ -73,7 +73,7 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
                u8 *wsrc = walk->src.virt.addr;
                u8 *wdst = walk->dst.virt.addr;
 
-               fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+               fpu_enabled = cast5_fpu_begin(false, nbytes);
 
                /* Process multi-block batch */
                if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
@@ -102,10 +102,9 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
                } while (nbytes >= bsize);
 
 done:
+               cast5_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, walk, nbytes);
        }
-
-       cast5_fpu_end(fpu_enabled);
        return err;
 }
 
@@ -226,7 +225,7 @@ static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
 static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
                       struct scatterlist *src, unsigned int nbytes)
 {
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        struct blkcipher_walk walk;
        int err;
 
@@ -235,12 +234,11 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
        desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
        while ((nbytes = walk.nbytes)) {
-               fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+               fpu_enabled = cast5_fpu_begin(false, nbytes);
                nbytes = __cbc_decrypt(desc, &walk);
+               cast5_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, &walk, nbytes);
        }
-
-       cast5_fpu_end(fpu_enabled);
        return err;
 }
 
@@ -309,7 +307,7 @@ static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
 static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
                     struct scatterlist *src, unsigned int nbytes)
 {
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        struct blkcipher_walk walk;
        int err;
 
@@ -318,13 +316,12 @@ static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
        desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
        while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
-               fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+               fpu_enabled = cast5_fpu_begin(false, nbytes);
                nbytes = __ctr_crypt(desc, &walk);
+               cast5_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, &walk, nbytes);
        }
 
-       cast5_fpu_end(fpu_enabled);
-
        if (walk.nbytes) {
                ctr_crypt_final(desc, &walk);
                err = blkcipher_walk_done(desc, &walk, 0);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 50e684768c55..8caf9ba8c1da 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -205,19 +205,33 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void cast6_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       cast6_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void cast6_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = CAST6_BLOCK_SIZE;
        struct crypt_priv *ctx = priv;
        int i;
 
-       ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
        if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+               ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
                cast6_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+               cast6_fpu_end_rt(ctx);
                return;
        }
-
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                __cast6_encrypt(ctx->ctx, srcdst, srcdst);
 }
@@ -228,10 +242,10 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        struct crypt_priv *ctx = priv;
        int i;
 
-       ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
        if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+               ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
                cast6_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+               cast6_fpu_end_rt(ctx);
                return;
        }
 
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 1e6af1b35f7b..e7809fd2a4fd 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -81,23 +81,24 @@ static int chacha20_simd(struct skcipher_request *req)
 
        crypto_chacha20_init(state, ctx, walk.iv);
 
-       kernel_fpu_begin();
-
        while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+               kernel_fpu_begin();
+
                chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
                                rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+               kernel_fpu_end();
                err = skcipher_walk_done(&walk,
                                         walk.nbytes % CHACHA20_BLOCK_SIZE);
        }
 
        if (walk.nbytes) {
+               kernel_fpu_begin();
                chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
                                walk.nbytes);
+               kernel_fpu_end();
                err = skcipher_walk_done(&walk, 0);
        }
 
-       kernel_fpu_end();
-
        return err;
 }
 
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index d61e57960fe0..c67560d9718a 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -40,7 +40,7 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
        void *ctx = crypto_blkcipher_ctx(desc->tfm);
        const unsigned int bsize = 128 / 8;
        unsigned int nbytes, i, func_bytes;
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        int err;
 
        err = blkcipher_walk_virt(desc, walk);
@@ -50,7 +50,7 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
                u8 *wdst = walk->dst.virt.addr;
 
                fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-                                            desc, fpu_enabled, nbytes);
+                                            desc, false, nbytes);
 
                for (i = 0; i < gctx->num_funcs; i++) {
                        func_bytes = bsize * gctx->funcs[i].num_blocks;
@@ -72,10 +72,10 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
                }
 
 done:
+               glue_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, walk, nbytes);
        }
 
-       glue_fpu_end(fpu_enabled);
        return err;
 }
 
@@ -192,7 +192,7 @@ int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
                            struct scatterlist *src, unsigned int nbytes)
 {
        const unsigned int bsize = 128 / 8;
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        struct blkcipher_walk walk;
        int err;
 
@@ -201,12 +201,12 @@ int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
 
        while ((nbytes = walk.nbytes)) {
                fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-                                            desc, fpu_enabled, nbytes);
+                                            desc, false, nbytes);
                nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
+               glue_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, &walk, nbytes);
        }
 
-       glue_fpu_end(fpu_enabled);
        return err;
 }
 EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit);
@@ -275,7 +275,7 @@ int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
                          struct scatterlist *src, unsigned int nbytes)
 {
        const unsigned int bsize = 128 / 8;
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        struct blkcipher_walk walk;
        int err;
 
@@ -284,13 +284,12 @@ int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
 
        while ((nbytes = walk.nbytes) >= bsize) {
                fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-                                            desc, fpu_enabled, nbytes);
+                                            desc, false, nbytes);
                nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
+               glue_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, &walk, nbytes);
        }
 
-       glue_fpu_end(fpu_enabled);
-
        if (walk.nbytes) {
                glue_ctr_crypt_final_128bit(
                        gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
@@ -380,7 +379,7 @@ int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
                          void *tweak_ctx, void *crypt_ctx)
 {
        const unsigned int bsize = 128 / 8;
-       bool fpu_enabled = false;
+       bool fpu_enabled;
        struct blkcipher_walk walk;
        int err;
 
@@ -393,21 +392,21 @@ int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
 
        /* set minimum length to bsize, for tweak_fn */
        fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-                                    desc, fpu_enabled,
+                                    desc, false,
                                     nbytes < bsize ? bsize : nbytes);
-
        /* calculate first value of T */
        tweak_fn(tweak_ctx, walk.iv, walk.iv);
+       glue_fpu_end(fpu_enabled);
 
        while (nbytes) {
+               fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+                               desc, false, nbytes);
                nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk);
 
+               glue_fpu_end(fpu_enabled);
                err = blkcipher_walk_done(desc, &walk, nbytes);
                nbytes = walk.nbytes;
        }
-
-       glue_fpu_end(fpu_enabled);
-
        return err;
 }
 EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit);
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 870f6d812a2d..5c806bf39f1d 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -184,6 +184,21 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       serpent_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = SERPENT_BLOCK_SIZE;
@@ -199,10 +214,12 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        }
 
        while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
                nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
        }
+       serpent_fpu_end_rt(ctx);
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                __serpent_encrypt(ctx->ctx, srcdst, srcdst);
@@ -223,10 +240,12 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        }
 
        while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
+               kernel_fpu_resched();
                serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
                srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
                nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
        }
+       serpent_fpu_end_rt(ctx);
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
                __serpent_decrypt(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 6f778d3daa22..46dcbdbd0518 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -218,16 +218,31 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       serpent_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = SERPENT_BLOCK_SIZE;
        struct crypt_priv *ctx = priv;
        int i;
 
-       ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
        if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+               ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
                serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
+               serpent_fpu_end_rt(ctx);
                return;
        }
 
@@ -241,10 +256,10 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        struct crypt_priv *ctx = priv;
        int i;
 
-       ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
        if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+               ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
                serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
+               serpent_fpu_end_rt(ctx);
                return;
        }
 
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index ac0e831943f5..d35f607d067f 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -187,16 +187,31 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       serpent_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = SERPENT_BLOCK_SIZE;
        struct crypt_priv *ctx = priv;
        int i;
 
-       ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
        if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+               ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
                serpent_enc_blk_xway(ctx->ctx, srcdst, srcdst);
+               serpent_fpu_end_rt(ctx);
                return;
        }
 
@@ -210,10 +225,10 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
        struct crypt_priv *ctx = priv;
        int i;
 
-       ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
        if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+               ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
                serpent_dec_blk_xway(ctx->ctx, srcdst, srcdst);
+               serpent_fpu_end_rt(ctx);
                return;
        }
 
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b7a3904b953c..de00fe24927e 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -218,6 +218,21 @@ struct crypt_priv {
        bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void twofish_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       twofish_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void twofish_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
        const unsigned int bsize = TF_BLOCK_SIZE;
@@ -228,12 +243,16 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 
        if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
                twofish_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+               twofish_fpu_end_rt(ctx);
                return;
        }
 
-       for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+       for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3) {
+               kernel_fpu_resched();
                twofish_enc_blk_3way(ctx->ctx, srcdst, srcdst);
+       }
 
+       twofish_fpu_end_rt(ctx);
        nbytes %= bsize * 3;
 
        for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
@@ -250,11 +269,15 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 
        if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
                twofish_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+               twofish_fpu_end_rt(ctx);
                return;
        }
 
-       for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+       for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3) {
+               kernel_fpu_resched();
                twofish_dec_blk_3way(ctx->ctx, srcdst, srcdst);
+       }
+       twofish_fpu_end_rt(ctx);
 
        nbytes %= bsize * 3;
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 60e21ccfb6d6..0e27f35febe7 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -133,7 +133,7 @@ static long syscall_trace_enter(struct pt_regs *regs)
 
 #define EXIT_TO_USERMODE_LOOP_FLAGS                            \
        (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |   \
-        _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
+        _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
 
 static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
@@ -148,9 +148,16 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
                /* We have work to do. */
                local_irq_enable();
 
-               if (cached_flags & _TIF_NEED_RESCHED)
+               if (cached_flags & _TIF_NEED_RESCHED_MASK)
                        schedule();
 
+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
+               if (unlikely(current->forced_info.si_signo)) {
+                       struct task_struct *t = current;
+                       force_sig_info(t->forced_info.si_signo, &t->forced_info, t);
+                       t->forced_info.si_signo = 0;
+               }
+#endif
                if (cached_flags & _TIF_UPROBE)
                        uprobe_notify_resume(regs);
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 60c4c342316c..cd0c7c56e2dd 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -350,8 +350,25 @@ END(ret_from_exception)
 ENTRY(resume_kernel)
        DISABLE_INTERRUPTS(CLBR_ANY)
 .Lneed_resched:
+       # preempt count == 0 + NEED_RS set?
        cmpl    $0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
        jnz     restore_all
+#else
+       jz test_int_off
+
+       # atleast preempt count == 0 ?
+       cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+       jne restore_all
+
+       movl    PER_CPU_VAR(current_task), %ebp
+       cmpl    $0,TASK_TI_preempt_lazy_count(%ebp)     # non-zero preempt_lazy_count ?
+       jnz     restore_all
+
+       testl   $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp)
+       jz      restore_all
+test_int_off:
+#endif
        testl   $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
        jz      restore_all
        call    preempt_schedule_irq
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 164cd7529f0b..75d42cb8a7c9 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -633,7 +633,23 @@ retint_kernel:
        btl     $9, EFLAGS(%rsp)                /* were interrupts off? */
        jnc     1f
 0:     cmpl    $0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
        jnz     1f
+#else
+       jz      do_preempt_schedule_irq
+
+       # atleast preempt count == 0 ?
+       cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+       jnz     1f
+
+       movq    PER_CPU_VAR(current_task), %rcx
+       cmpl    $0, TASK_TI_preempt_lazy_count(%rcx)
+       jnz     1f
+
+       bt      $TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx)
+       jnc     1f
+do_preempt_schedule_irq:
+#endif
        call    preempt_schedule_irq
        jmp     0b
 1:
@@ -988,6 +1004,7 @@ bad_gs:
        jmp     2b
        .previous
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(do_softirq_own_stack)
        pushq   %rbp
@@ -998,6 +1015,7 @@ ENTRY(do_softirq_own_stack)
        leaveq
        ret
 ENDPROC(do_softirq_own_stack)
+#endif
 
 #ifdef CONFIG_XEN
 idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index a9caac9d4a72..18b31f22ca5d 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -25,6 +25,7 @@ extern void __kernel_fpu_begin(void);
 extern void __kernel_fpu_end(void);
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
+extern void kernel_fpu_resched(void);
 extern bool irq_fpu_usable(void);
 
 /*
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 7f2dbd91fc74..22992c837795 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -86,17 +86,46 @@ static __always_inline void __preempt_count_sub(int val)
  * a decrement which hits zero means we have no preempt_count and should
  * reschedule.
  */
-static __always_inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool ____preempt_count_dec_and_test(void)
 {
        GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
 }
 
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+       if (____preempt_count_dec_and_test())
+               return true;
+#ifdef CONFIG_PREEMPT_LAZY
+       if (current_thread_info()->preempt_lazy_count)
+               return false;
+       return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
+       return false;
+#endif
+}
+
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
+#ifdef CONFIG_PREEMPT_LAZY
+       u32 tmp;
+
+       tmp = raw_cpu_read_4(__preempt_count);
+       if (tmp == preempt_offset)
+               return true;
+
+       /* preempt count == 0 ? */
+       tmp &= ~PREEMPT_NEED_RESCHED;
+       if (tmp)
+               return false;
+       if (current_thread_info()->preempt_lazy_count)
+               return false;
+       return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
        return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
+#endif
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 5f9012ff52ed..39117e57caf2 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -28,6 +28,19 @@ typedef struct {
 #define SA_IA32_ABI    0x02000000u
 #define SA_X32_ABI     0x01000000u
 
+/*
+ * Because some traps use the IST stack, we must keep preemption
+ * disabled while calling do_trap(), but do_trap() may call
+ * force_sig_info() which will grab the signal spin_locks for the
+ * task, which in PREEMPT_RT_FULL are mutexes.  By defining
+ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set
+ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the
+ * trap.
+ */
+#if defined(CONFIG_PREEMPT_RT_FULL)
+#define ARCH_RT_DELAYS_SIGNAL_SEND
+#endif
+
 #ifndef CONFIG_COMPAT
 typedef sigset_t compat_sigset_t;
 #endif
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 371b3a4af000..06613a805b25 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -60,7 +60,7 @@
  */
 static __always_inline void boot_init_stack_canary(void)
 {
-       u64 canary;
+       u64 uninitialized_var(canary);
        u64 tsc;
 
 #ifdef CONFIG_X86_64
@@ -71,8 +71,14 @@ static __always_inline void boot_init_stack_canary(void)
         * of randomness. The TSC only matters for very early init,
         * there it already has some randomness on most systems. Later
         * on during the bootup the random pool has true entropy too.
+        * For preempt-rt we need to weaken the randomness a bit, as
+        * we can't call into the random generator from atomic context
+        * due to locking constraints. We just leave canary
+        * uninitialized and use the TSC based randomness on top of it.
         */
+#ifndef CONFIG_PREEMPT_RT_FULL
        get_random_bytes(&canary, sizeof(canary));
+#endif
        tsc = rdtsc();
        canary += tsc + (tsc << 32UL);
        canary &= CANARY_MASK;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 95ff2d7f553f..b1c9129f64fc 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -56,11 +56,14 @@ struct task_struct;
 struct thread_info {
        unsigned long           flags;          /* low level flags */
        u32                     status;         /* thread synchronous flags */
+       int                     preempt_lazy_count;     /* 0 => lazy preemptable
+                                                         <0 => BUG */
 };
 
 #define INIT_THREAD_INFO(tsk)                  \
 {                                              \
        .flags          = 0,                    \
+       .preempt_lazy_count = 0,                \
 }
 
 #define init_stack             (init_thread_union.stack)
@@ -69,6 +72,10 @@ struct thread_info {
 
 #include <asm/asm-offsets.h>
 
+#define GET_THREAD_INFO(reg) \
+       _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
+       _ASM_SUB $(THREAD_SIZE),reg ;
+
 #endif
 
 /*
@@ -85,6 +92,7 @@ struct thread_info {
 #define TIF_SYSCALL_EMU                6       /* syscall emulation active */
 #define TIF_SYSCALL_AUDIT      7       /* syscall auditing active */
 #define TIF_SECCOMP            8       /* secure computing */
+#define TIF_NEED_RESCHED_LAZY  9       /* lazy rescheduling necessary */
 #define TIF_USER_RETURN_NOTIFY 11      /* notify kernel of userspace return */
 #define TIF_UPROBE             12      /* breakpointed or singlestepping */
 #define TIF_PATCH_PENDING      13      /* pending live patching update */
@@ -112,6 +120,7 @@ struct thread_info {
 #define _TIF_SYSCALL_EMU       (1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT     (1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP           (1 << TIF_SECCOMP)
+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_USER_RETURN_NOTIFY        (1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE            (1 << TIF_UPROBE)
 #define _TIF_PATCH_PENDING     (1 << TIF_PATCH_PENDING)
@@ -153,6 +162,8 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
+#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
+
 #define STACK_WARN             (THREAD_SIZE/8)
 
 /*
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 96a8a68f9c79..c9af5afebc4a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1688,19 +1688,20 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
        return false;
 }
 
-static inline bool ioapic_irqd_mask(struct irq_data *data)
+static inline bool ioapic_prepare_move(struct irq_data *data)
 {
        /* If we are moving the irq we need to mask it */
        if (unlikely(irqd_is_setaffinity_pending(data))) {
-               mask_ioapic_irq(data);
+               if (!irqd_irq_masked(data))
+                       mask_ioapic_irq(data);
                return true;
        }
        return false;
 }
 
-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
+static inline void ioapic_finish_move(struct irq_data *data, bool moveit)
 {
-       if (unlikely(masked)) {
+       if (unlikely(moveit)) {
                /* Only migrate the irq if the ack has been received.
                 *
                 * On rare occasions the broadcast level triggered ack gets
@@ -1729,15 +1730,17 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
                 */
                if (!io_apic_level_ack_pending(data->chip_data))
                        irq_move_masked_irq(data);
-               unmask_ioapic_irq(data);
+               /* If the irq is masked in the core, leave it */
+               if (!irqd_irq_masked(data))
+                       unmask_ioapic_irq(data);
        }
 }
 #else
-static inline bool ioapic_irqd_mask(struct irq_data *data)
+static inline bool ioapic_prepare_move(struct irq_data *data)
 {
        return false;
 }
-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
+static inline void ioapic_finish_move(struct irq_data *data, bool moveit)
 {
 }
 #endif
@@ -1746,11 +1749,11 @@ static void ioapic_ack_level(struct irq_data *irq_data)
 {
        struct irq_cfg *cfg = irqd_cfg(irq_data);
        unsigned long v;
-       bool masked;
+       bool moveit;
        int i;
 
        irq_complete_move(cfg);
-       masked = ioapic_irqd_mask(irq_data);
+       moveit = ioapic_prepare_move(irq_data);
 
        /*
         * It appears there is an erratum which affects at least version 0x11
@@ -1805,7 +1808,7 @@ static void ioapic_ack_level(struct irq_data *irq_data)
                eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
        }
 
-       ioapic_irqd_unmask(irq_data, masked);
+       ioapic_finish_move(irq_data, moveit);
 }
 
 static void ioapic_ir_ack_level(struct irq_data *irq_data)
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 76417a9aab73..62c3e27c8e1c 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -38,6 +38,7 @@ void common(void) {
 
        BLANK();
        OFFSET(TASK_TI_flags, task_struct, thread_info.flags);
+       OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count);
        OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
 
        BLANK();
@@ -94,6 +95,7 @@ void common(void) {
 
        BLANK();
        DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+       DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
 
        /* TLB state for the entry code */
        OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 7f85b76f43bc..9e74b805070f 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
+#include <linux/swork.h>
 
 #include "mce-internal.h"
 
@@ -86,13 +87,43 @@ static void mce_do_trigger(struct work_struct *work)
 
 static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
 
-
-void mce_work_trigger(void)
+static void __mce_work_trigger(struct swork_event *event)
 {
        if (mce_helper[0])
                schedule_work(&mce_trigger_work);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static bool notify_work_ready __read_mostly;
+static struct swork_event notify_work;
+
+static int mce_notify_work_init(void)
+{
+       int err;
+
+       err = swork_get();
+       if (err)
+               return err;
+
+       INIT_SWORK(&notify_work, __mce_work_trigger);
+       notify_work_ready = true;
+       return 0;
+}
+
+void mce_work_trigger(void)
+{
+       if (notify_work_ready)
+               swork_queue(&notify_work);
+}
+
+#else
+void mce_work_trigger(void)
+{
+       __mce_work_trigger(NULL);
+}
+static inline int mce_notify_work_init(void) { return 0; }
+#endif
+
 static ssize_t
 show_trigger(struct device *s, struct device_attribute *attr, char *buf)
 {
@@ -356,7 +387,7 @@ static __init int dev_mcelog_init_device(void)
 
                return err;
        }
-
+       mce_notify_work_init();
        mce_register_decode_chain(&dev_mcelog_nb);
        return 0;
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 98e4e4dc4a3b..5cce2ee3b9f6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -42,6 +42,7 @@
 #include <linux/debugfs.h>
 #include <linux/irq_work.h>
 #include <linux/export.h>
+#include <linux/jiffies.h>
 #include <linux/jump_label.h>
 
 #include <asm/intel-family.h>
@@ -1365,7 +1366,7 @@ int memory_failure(unsigned long pfn, int vector, int flags)
 static unsigned long check_interval = INITIAL_CHECK_INTERVAL;
 
 static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
-static DEFINE_PER_CPU(struct timer_list, mce_timer);
+static DEFINE_PER_CPU(struct hrtimer, mce_timer);
 
 static unsigned long mce_adjust_timer_default(unsigned long interval)
 {
@@ -1374,27 +1375,19 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
 
 static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
 
-static void __start_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct hrtimer *t, unsigned long iv)
 {
-       unsigned long when = jiffies + interval;
-       unsigned long flags;
-
-       local_irq_save(flags);
-
-       if (!timer_pending(t) || time_before(when, t->expires))
-               mod_timer(t, round_jiffies(when));
+       if (!iv)
+               return;
 
-       local_irq_restore(flags);
+       hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL),
+                              0, HRTIMER_MODE_REL_PINNED);
 }
 
-static void mce_timer_fn(unsigned long data)
+static  enum hrtimer_restart mce_timer_fn(struct hrtimer *timer)
 {
-       struct timer_list *t = this_cpu_ptr(&mce_timer);
-       int cpu = smp_processor_id();
        unsigned long iv;
 
-       WARN_ON(cpu != data);
-
        iv = __this_cpu_read(mce_next_interval);
 
        if (mce_available(this_cpu_ptr(&cpu_info))) {
@@ -1417,7 +1410,11 @@ static void mce_timer_fn(unsigned long data)
 
 done:
        __this_cpu_write(mce_next_interval, iv);
-       __start_timer(t, iv);
+       if (!iv)
+               return HRTIMER_NORESTART;
+
+       hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(iv)));
+       return HRTIMER_RESTART;
 }
 
 /*
@@ -1425,7 +1422,7 @@ static void mce_timer_fn(unsigned long data)
  */
 void mce_timer_kick(unsigned long interval)
 {
-       struct timer_list *t = this_cpu_ptr(&mce_timer);
+       struct hrtimer *t = this_cpu_ptr(&mce_timer);
        unsigned long iv = __this_cpu_read(mce_next_interval);
 
        __start_timer(t, interval);
@@ -1440,7 +1437,7 @@ static void mce_timer_delete_all(void)
        int cpu;
 
        for_each_online_cpu(cpu)
-               del_timer_sync(&per_cpu(mce_timer, cpu));
+               hrtimer_cancel(&per_cpu(mce_timer, cpu));
 }
 
 /*
@@ -1769,7 +1766,7 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
        }
 }
 
-static void mce_start_timer(struct timer_list *t)
+static void mce_start_timer(struct hrtimer *t)
 {
        unsigned long iv = check_interval * HZ;
 
@@ -1782,18 +1779,19 @@ static void mce_start_timer(struct timer_list *t)
 
 static void __mcheck_cpu_setup_timer(void)
 {
-       struct timer_list *t = this_cpu_ptr(&mce_timer);
-       unsigned int cpu = smp_processor_id();
+       struct hrtimer *t = this_cpu_ptr(&mce_timer);
 
-       setup_pinned_timer(t, mce_timer_fn, cpu);
+       hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       t->function = mce_timer_fn;
 }
 
 static void __mcheck_cpu_init_timer(void)
 {
-       struct timer_list *t = this_cpu_ptr(&mce_timer);
-       unsigned int cpu = smp_processor_id();
+       struct hrtimer *t = this_cpu_ptr(&mce_timer);
+
+       hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       t->function = mce_timer_fn;
 
-       setup_pinned_timer(t, mce_timer_fn, cpu);
        mce_start_timer(t);
 }
 
@@ -2309,7 +2307,7 @@ static int mce_cpu_dead(unsigned int cpu)
 
 static int mce_cpu_online(unsigned int cpu)
 {
-       struct timer_list *t = this_cpu_ptr(&mce_timer);
+       struct hrtimer *t = this_cpu_ptr(&mce_timer);
        int ret;
 
        mce_device_create(cpu);
@@ -2326,10 +2324,10 @@ static int mce_cpu_online(unsigned int cpu)
 
 static int mce_cpu_pre_down(unsigned int cpu)
 {
-       struct timer_list *t = this_cpu_ptr(&mce_timer);
+       struct hrtimer *t = this_cpu_ptr(&mce_timer);
 
        mce_disable_cpu();
-       del_timer_sync(t);
+       hrtimer_cancel(t);
        mce_threshold_remove_device(cpu);
        mce_device_remove(cpu);
        return 0;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2ea85b32421a..6914dc569d1e 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -138,6 +138,18 @@ void kernel_fpu_end(void)
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
+void kernel_fpu_resched(void)
+{
+       WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+
+       if (should_resched(PREEMPT_OFFSET)) {
+               kernel_fpu_end();
+               cond_resched();
+               kernel_fpu_begin();
+       }
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_resched);
+
 /*
  * Save the FPU state (mark it for reload if necessary):
  *
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 95600a99ae93..9192d76085ba 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -130,6 +130,7 @@ void irq_ctx_init(int cpu)
               cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
        struct irq_stack *irqstk;
@@ -146,6 +147,7 @@ void do_softirq_own_stack(void)
 
        call_on_stack(__do_softirq, isp);
 }
+#endif
 
 bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 5224c6099184..9b2b1f0409c5 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -38,6 +38,7 @@
 #include <linux/io.h>
 #include <linux/kdebug.h>
 #include <linux/syscalls.h>
+#include <linux/highmem.h>
 
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
@@ -198,6 +199,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+       int i;
+
+       /*
+        * Clear @prev's kmap_atomic mappings
+        */
+       for (i = 0; i < prev_p->kmap_idx; i++) {
+               int idx = i + KM_TYPE_NR * smp_processor_id();
+               pte_t *ptep = kmap_pte - idx;
+
+               kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx));
+       }
+       /*
+        * Restore @next_p's kmap_atomic mappings
+        */
+       for (i = 0; i < next_p->kmap_idx; i++) {
+               int idx = i + KM_TYPE_NR * smp_processor_id();
+
+               if (!pte_none(next_p->kmap_pte[i]))
+                       set_pte(kmap_pte - idx, next_p->kmap_pte[i]);
+       }
+}
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
 
 /*
  *     switch_to(x,y) should switch tasks from x to y.
@@ -273,6 +303,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
                __switch_to_xtra(prev_p, next_p, tss);
 
+       switch_kmaps(prev_p, next_p);
+
        /*
         * Leave lazy mode, flushing any hypercalls made here.
         * This must be done before restoring TLS segments so
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 13dfb55b84db..dd66f629d1d0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2136,7 +2136,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
        apic->vcpu = vcpu;
 
        hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-                    HRTIMER_MODE_ABS_PINNED);
+                    HRTIMER_MODE_ABS_PINNED_HARD);
        apic->lapic_timer.timer.function = apic_timer_fn;
 
        /*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3856828ee1dc..407658146ae1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6287,6 +6287,13 @@ int kvm_arch_init(void *opaque)
                goto out;
        }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+               printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n");
+               return -EOPNOTSUPP;
+       }
+#endif
+
        r = kvm_mmu_module_init();
        if (r)
                goto out_free_percpu;
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 6d18b70ed5a9..f752724c22e8 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap);
  */
 void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
+       pte_t pte = mk_pte(page, prot);
        unsigned long vaddr;
        int idx, type;
 
-       preempt_disable();
+       preempt_disable_nort();
        pagefault_disable();
 
        if (!PageHighMem(page))
@@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
        idx = type + KM_TYPE_NR*smp_processor_id();
        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
        BUG_ON(!pte_none(*(kmap_pte-idx)));
-       set_pte(kmap_pte-idx, mk_pte(page, prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+       current->kmap_pte[type] = pte;
+#endif
+       set_pte(kmap_pte-idx, pte);
        arch_flush_lazy_mmu_mode();
 
        return (void *)vaddr;
@@ -88,6 +92,9 @@ void __kunmap_atomic(void *kvaddr)
                 * is a bad idea also, in case the page changes cacheability
                 * attributes or becomes a protected page in a hypervisor.
                 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+               current->kmap_pte[type] = __pte(0);
+#endif
                kpte_clear_flush(kmap_pte-idx, vaddr);
                kmap_atomic_idx_pop();
                arch_flush_lazy_mmu_mode();
@@ -100,7 +107,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 
        pagefault_enable();
-       preempt_enable();
+       preempt_enable_nort();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index ada98b39b8ad..585f6829653b 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -56,6 +56,7 @@ EXPORT_SYMBOL_GPL(iomap_free);
 
 void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 {
+       pte_t pte = pfn_pte(pfn, prot);
        unsigned long vaddr;
        int idx, type;
 
@@ -65,7 +66,12 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
        type = kmap_atomic_idx_push();
        idx = type + KM_TYPE_NR * smp_processor_id();
        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-       set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
+       WARN_ON(!pte_none(*(kmap_pte - idx)));
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+       current->kmap_pte[type] = pte;
+#endif
+       set_pte(kmap_pte - idx, pte);
        arch_flush_lazy_mmu_mode();
 
        return (void *)vaddr;
@@ -113,6 +119,9 @@ iounmap_atomic(void __iomem *kvaddr)
                 * is a bad idea also, in case the page changes cacheability
                 * attributes or becomes a protected page in a hypervisor.
                 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+               current->kmap_pte[type] = __pte(0);
+#endif
                kpte_clear_flush(kmap_pte-idx, vaddr);
                kmap_atomic_idx_pop();
        }
diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h
index bb1fe6c1816e..8a22f1e7b6c9 100644
--- a/arch/xtensa/include/asm/spinlock_types.h
+++ b/arch/xtensa/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
        volatile unsigned int slock;
 } arch_spinlock_t;
diff --git a/block/blk-core.c b/block/blk-core.c
index 6aa2bc4e9652..f005077ae291 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -116,6 +116,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 
        INIT_LIST_HEAD(&rq->queuelist);
        INIT_LIST_HEAD(&rq->timeout_list);
+#ifdef CONFIG_PREEMPT_RT_FULL
+       INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
+#endif
        rq->cpu = -1;
        rq->q = q;
        rq->__sector = (sector_t) -1;
@@ -280,7 +283,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
 void blk_start_queue(struct request_queue *q)
 {
        lockdep_assert_held(q->queue_lock);
-       WARN_ON(!in_interrupt() && !irqs_disabled());
+       WARN_ON_NONRT(!in_interrupt() && !irqs_disabled());
        WARN_ON_ONCE(q->mq_ops);
 
        queue_flag_clear(QUEUE_FLAG_STOPPED, q);
@@ -812,12 +815,21 @@ void blk_queue_exit(struct request_queue *q)
        percpu_ref_put(&q->q_usage_counter);
 }
 
+static void blk_queue_usage_counter_release_swork(struct swork_event *sev)
+{
+       struct request_queue *q =
+               container_of(sev, struct request_queue, mq_pcpu_wake);
+
+       wake_up_all(&q->mq_freeze_wq);
+}
+
 static void blk_queue_usage_counter_release(struct percpu_ref *ref)
 {
        struct request_queue *q =
                container_of(ref, struct request_queue, q_usage_counter);
 
-       wake_up_all(&q->mq_freeze_wq);
+       if (wq_has_sleeper(&q->mq_freeze_wq))
+               swork_queue(&q->mq_pcpu_wake);
 }
 
 static void blk_rq_timed_out_timer(unsigned long data)
@@ -894,6 +906,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
        __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
 
        init_waitqueue_head(&q->mq_freeze_wq);
+       INIT_SWORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_swork);
 
        /*
         * Init percpu_ref in atomic mode so that it's faster to shutdown.
@@ -3313,7 +3326,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
                blk_run_queue_async(q);
        else
                __blk_run_queue(q);
-       spin_unlock(q->queue_lock);
+       spin_unlock_irq(q->queue_lock);
 }
 
 static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -3361,7 +3374,6 @@ EXPORT_SYMBOL(blk_check_plugged);
 void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
        struct request_queue *q;
-       unsigned long flags;
        struct request *rq;
        LIST_HEAD(list);
        unsigned int depth;
@@ -3381,11 +3393,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
        q = NULL;
        depth = 0;
 
-       /*
-        * Save and disable interrupts here, to avoid doing it for every
-        * queue lock we have to take.
-        */
-       local_irq_save(flags);
        while (!list_empty(&list)) {
                rq = list_entry_rq(list.next);
                list_del_init(&rq->queuelist);
@@ -3398,7 +3405,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
                                queue_unplugged(q, depth, from_schedule);
                        q = rq->q;
                        depth = 0;
-                       spin_lock(q->queue_lock);
+                       spin_lock_irq(q->queue_lock);
                }
 
                /*
@@ -3425,8 +3432,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
         */
        if (q)
                queue_unplugged(q, depth, from_schedule);
-
-       local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)
@@ -3638,6 +3643,8 @@ int __init blk_dev_init(void)
        if (!kblockd_workqueue)
                panic("Failed to create kblockd\n");
 
+       BUG_ON(swork_get());
+
        request_cachep = kmem_cache_create("blkdev_requests",
                        sizeof(struct request), 0, SLAB_PANIC, NULL);
 
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index f23311e4b201..ca9ea624f159 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/sched/task.h>
+#include <linux/delay.h>
 
 #include "blk.h"
 
@@ -118,7 +119,7 @@ static void ioc_release_fn(struct work_struct *work)
                        spin_unlock(q->queue_lock);
                } else {
                        spin_unlock_irqrestore(&ioc->lock, flags);
-                       cpu_relax();
+                       cpu_chill();
                        spin_lock_irqsave_nested(&ioc->lock, flags, 1);
                }
        }
@@ -202,7 +203,7 @@ void put_io_context_active(struct io_context *ioc)
                                spin_unlock(icq->q->queue_lock);
                        } else {
                                spin_unlock_irqrestore(&ioc->lock, flags);
-                               cpu_relax();
+                               cpu_chill();
                                goto retry;
                        }
                }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index eac444804736..a6314b82273e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -339,6 +339,9 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
        /* tag was already set */
        rq->extra_len = 0;
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+       INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
+#endif
        INIT_LIST_HEAD(&rq->timeout_list);
        rq->timeout = 0;
 
@@ -533,12 +536,24 @@ void blk_mq_end_request(struct request *rq, blk_status_t error)
 }
 EXPORT_SYMBOL(blk_mq_end_request);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+void __blk_mq_complete_request_remote_work(struct work_struct *work)
+{
+       struct request *rq = container_of(work, struct request, work);
+
+       rq->q->softirq_done_fn(rq);
+}
+
+#else
+
 static void __blk_mq_complete_request_remote(void *data)
 {
        struct request *rq = data;
 
        rq->q->softirq_done_fn(rq);
 }
+#endif
 
 static void __blk_mq_complete_request(struct request *rq)
 {
@@ -558,19 +573,27 @@ static void __blk_mq_complete_request(struct request *rq)
                return;
        }
 
-       cpu = get_cpu();
+       cpu = get_cpu_light();
        if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
                shared = cpus_share_cache(cpu, ctx->cpu);
 
        if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+               /*
+                * We could force QUEUE_FLAG_SAME_FORCE then we would not get in
+                * here. But we could try to invoke it one the CPU like this.
+                */
+               schedule_work_on(ctx->cpu, &rq->work);
+#else
                rq->csd.func = __blk_mq_complete_request_remote;
                rq->csd.info = rq;
                rq->csd.flags = 0;
                smp_call_function_single_async(ctx->cpu, &rq->csd);
+#endif
        } else {
                rq->q->softirq_done_fn(rq);
        }
-       put_cpu();
+       put_cpu_light();
 }
 
 /**
@@ -1238,14 +1261,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
                return;
 
        if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-               int cpu = get_cpu();
+               int cpu = get_cpu_light();
                if (cpumask_test_cpu(cpu, hctx->cpumask)) {
                        __blk_mq_run_hw_queue(hctx);
-                       put_cpu();
+                       put_cpu_light();
                        return;
                }
 
-               put_cpu();
+               put_cpu_light();
        }
 
        kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
@@ -2863,10 +2886,9 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
        kt = nsecs;
 
        mode = HRTIMER_MODE_REL;
-       hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+       hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode, current);
        hrtimer_set_expires(&hs.timer, kt);
 
-       hrtimer_init_sleeper(&hs, current);
        do {
                if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
                        break;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 877237e09083..d944750bade0 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -98,12 +98,12 @@ static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
  */
 static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
 {
-       return __blk_mq_get_ctx(q, get_cpu());
+       return __blk_mq_get_ctx(q, get_cpu_light());
 }
 
 static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
 {
-       put_cpu();
+       put_cpu_light();
 }
 
 struct blk_mq_alloc_data {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 01e2b353a2b9..e8c0d4945f5a 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -53,6 +53,7 @@ static void trigger_softirq(void *data)
                raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 
 /*
@@ -91,6 +92,7 @@ static int blk_softirq_cpu_dead(unsigned int cpu)
                         this_cpu_ptr(&blk_cpu_done));
        raise_softirq_irqoff(BLOCK_SOFTIRQ);
        local_irq_enable();
+       preempt_check_resched_rt();
 
        return 0;
 }
@@ -143,6 +145,7 @@ void __blk_complete_request(struct request *req)
                goto do_local;
 
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 
 /**
diff --git a/block/bounce.c b/block/bounce.c
index 1d05c422c932..0101ffefddc4 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -66,11 +66,11 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
        unsigned long flags;
        unsigned char *vto;
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        vto = kmap_atomic(to->bv_page);
        memcpy(vto + to->bv_offset, vfrom, to->bv_len);
        kunmap_atomic(vto);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 }
 
 #else /* CONFIG_HIGHMEM */
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 50eb828db767..7bce92a6599a 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -731,13 +731,13 @@ EXPORT_SYMBOL_GPL(crypto_spawn_tfm2);
 
 int crypto_register_notifier(struct notifier_block *nb)
 {
-       return blocking_notifier_chain_register(&crypto_chain, nb);
+       return srcu_notifier_chain_register(&crypto_chain, nb);
 }
 EXPORT_SYMBOL_GPL(crypto_register_notifier);
 
 int crypto_unregister_notifier(struct notifier_block *nb)
 {
-       return blocking_notifier_chain_unregister(&crypto_chain, nb);
+       return srcu_notifier_chain_unregister(&crypto_chain, nb);
 }
 EXPORT_SYMBOL_GPL(crypto_unregister_notifier);
 
diff --git a/crypto/api.c b/crypto/api.c
index e485aed11ad0..089e648d2fa9 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(crypto_alg_list);
 DECLARE_RWSEM(crypto_alg_sem);
 EXPORT_SYMBOL_GPL(crypto_alg_sem);
 
-BLOCKING_NOTIFIER_HEAD(crypto_chain);
+SRCU_NOTIFIER_HEAD(crypto_chain);
 EXPORT_SYMBOL_GPL(crypto_chain);
 
 static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
@@ -236,10 +236,10 @@ int crypto_probing_notify(unsigned long val, void *v)
 {
        int ok;
 
-       ok = blocking_notifier_call_chain(&crypto_chain, val, v);
+       ok = srcu_notifier_call_chain(&crypto_chain, val, v);
        if (ok == NOTIFY_DONE) {
                request_module("cryptomgr");
-               ok = blocking_notifier_call_chain(&crypto_chain, val, v);
+               ok = srcu_notifier_call_chain(&crypto_chain, val, v);
        }
 
        return ok;
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 248f6ba41688..54b7985c8caa 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -37,6 +37,7 @@
 struct cryptd_cpu_queue {
        struct crypto_queue queue;
        struct work_struct work;
+       spinlock_t qlock;
 };
 
 struct cryptd_queue {
@@ -115,6 +116,7 @@ static int cryptd_init_queue(struct cryptd_queue *queue,
                cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu);
                crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
                INIT_WORK(&cpu_queue->work, cryptd_queue_worker);
+               spin_lock_init(&cpu_queue->qlock);
        }
        return 0;
 }
@@ -139,8 +141,10 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue,
        atomic_t *refcnt;
        bool may_backlog;
 
-       cpu = get_cpu();
-       cpu_queue = this_cpu_ptr(queue->cpu_queue);
+       cpu_queue = raw_cpu_ptr(queue->cpu_queue);
+       spin_lock_bh(&cpu_queue->qlock);
+       cpu = smp_processor_id();
+
        err = crypto_enqueue_request(&cpu_queue->queue, request);
 
        refcnt = crypto_tfm_ctx(request->tfm);
@@ -157,7 +161,7 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue,
        atomic_inc(refcnt);
 
 out_put_cpu:
-       put_cpu();
+       spin_unlock_bh(&cpu_queue->qlock);
 
        return err;
 }
@@ -173,16 +177,11 @@ static void cryptd_queue_worker(struct work_struct *work)
        cpu_queue = container_of(work, struct cryptd_cpu_queue, work);
        /*
         * Only handle one request at a time to avoid hogging crypto workqueue.
-        * preempt_disable/enable is used to prevent being preempted by
-        * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent
-        * cryptd_enqueue_request() being accessed from software interrupts.
         */
-       local_bh_disable();
-       preempt_disable();
+       spin_lock_bh(&cpu_queue->qlock);
        backlog = crypto_get_backlog(&cpu_queue->queue);
        req = crypto_dequeue_request(&cpu_queue->queue);
-       preempt_enable();
-       local_bh_enable();
+       spin_unlock_bh(&cpu_queue->qlock);
 
        if (!req)
                return;
diff --git a/crypto/internal.h b/crypto/internal.h
index f07320423191..333d985088fe 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -47,7 +47,7 @@ struct crypto_larval {
 
 extern struct list_head crypto_alg_list;
 extern struct rw_semaphore crypto_alg_sem;
-extern struct blocking_notifier_head crypto_chain;
+extern struct srcu_notifier_head crypto_chain;
 
 #ifdef CONFIG_PROC_FS
 void __init crypto_init_proc(void);
@@ -143,7 +143,7 @@ static inline int crypto_is_moribund(struct crypto_alg *alg)
 
 static inline void crypto_notify(unsigned long val, void *v)
 {
-       blocking_notifier_call_chain(&crypto_chain, val, v);
+       srcu_notifier_call_chain(&crypto_chain, val, v);
 }
 
 #endif /* _CRYPTO_INTERNAL_H */
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 2075e2c4e7df..c6b4e265c6bf 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -24,6 +24,7 @@
 #include <linux/cryptouser.h>
 #include <net/netlink.h>
 #include <linux/scatterlist.h>
+#include <linux/locallock.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/acompress.h>
 #include <crypto/internal/scompress.h>
@@ -34,6 +35,7 @@ static void * __percpu *scomp_src_scratches;
 static void * __percpu *scomp_dst_scratches;
 static int scomp_scratch_users;
 static DEFINE_MUTEX(scomp_lock);
+static DEFINE_LOCAL_IRQ_LOCK(scomp_scratches_lock);
 
 #ifdef CONFIG_NET
 static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg)
@@ -193,7 +195,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
        void **tfm_ctx = acomp_tfm_ctx(tfm);
        struct crypto_scomp *scomp = *tfm_ctx;
        void **ctx = acomp_request_ctx(req);
-       const int cpu = get_cpu();
+       const int cpu = local_lock_cpu(scomp_scratches_lock);
        u8 *scratch_src = *per_cpu_ptr(scomp_src_scratches, cpu);
        u8 *scratch_dst = *per_cpu_ptr(scomp_dst_scratches, cpu);
        int ret;
@@ -228,7 +230,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
                                         1);
        }
 out:
-       put_cpu();
+       local_unlock_cpu(scomp_scratches_lock);
        return ret;
 }
 
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 95eed442703f..50bc5b61d899 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -116,7 +116,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pending);
  * interrupt level
  */
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */
-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock);    /* For ACPI H/W except GPE registers */
+ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock);        /* For ACPI H/W except GPE registers */
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock);
 
 /* Mutex for _OSI support */
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index acb417b58bbb..ea49e08c263f 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -428,14 +428,14 @@ acpi_status acpi_hw_clear_acpi_status(void)
                          ACPI_BITMASK_ALL_FIXED_STATUS,
                          ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
 
-       lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+       raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
 
        /* Clear the fixed events in PM1 A/B */
 
        status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
                                        ACPI_BITMASK_ALL_FIXED_STATUS);
 
-       acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+       raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
 
        if (ACPI_FAILURE(status)) {
                goto exit;
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 34684ae89981..fb84983e1839 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -373,7 +373,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
                return_ACPI_STATUS(AE_BAD_PARAMETER);
        }
 
-       lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+       raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
 
        /*
         * At this point, we know that the parent register is one of the
@@ -434,7 +434,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
 
 unlock_and_exit:
 
-       acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+       raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
        return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index 586354788018..3a3c2a86437f 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(void)
                return_ACPI_STATUS (status);
        }
 
-       status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+       status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock);
        if (ACPI_FAILURE (status)) {
                return_ACPI_STATUS (status);
        }
@@ -145,7 +145,7 @@ void acpi_ut_mutex_terminate(void)
        /* Delete the spinlocks */
 
        acpi_os_delete_lock(acpi_gbl_gpe_lock);
-       acpi_os_delete_lock(acpi_gbl_hardware_lock);
+       acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
        acpi_os_delete_lock(acpi_gbl_reference_count_lock);
 
        /* Delete the reader/writer lock */
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index cc2f2e35f4c2..0f0bc86e02df 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -679,9 +679,9 @@ unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, unsigned char *b
        unsigned long flags;
        unsigned int consumed;
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        consumed = ata_sff_data_xfer32(qc, buf, buflen, rw);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 
        return consumed;
 }
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index cdd6f256da59..2269d379c92f 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -52,7 +52,7 @@ static void split_counters(unsigned int *cnt, unsigned int *inpr)
 /* A preserved old value of the events counter. */
 static unsigned int saved_count;
 
-static DEFINE_SPINLOCK(events_lock);
+static DEFINE_RAW_SPINLOCK(events_lock);
 
 static void pm_wakeup_timer_fn(unsigned long data);
 
@@ -180,9 +180,9 @@ void wakeup_source_add(struct wakeup_source *ws)
        ws->active = false;
        ws->last_time = ktime_get();
 
-       spin_lock_irqsave(&events_lock, flags);
+       raw_spin_lock_irqsave(&events_lock, flags);
        list_add_rcu(&ws->entry, &wakeup_sources);
-       spin_unlock_irqrestore(&events_lock, flags);
+       raw_spin_unlock_irqrestore(&events_lock, flags);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_add);
 
@@ -197,9 +197,9 @@ void wakeup_source_remove(struct wakeup_source *ws)
        if (WARN_ON(!ws))
                return;
 
-       spin_lock_irqsave(&events_lock, flags);
+       raw_spin_lock_irqsave(&events_lock, flags);
        list_del_rcu(&ws->entry);
-       spin_unlock_irqrestore(&events_lock, flags);
+       raw_spin_unlock_irqrestore(&events_lock, flags);
        synchronize_srcu(&wakeup_srcu);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_remove);
@@ -844,7 +844,7 @@ bool pm_wakeup_pending(void)
        unsigned long flags;
        bool ret = false;
 
-       spin_lock_irqsave(&events_lock, flags);
+       raw_spin_lock_irqsave(&events_lock, flags);
        if (events_check_enabled) {
                unsigned int cnt, inpr;
 
@@ -852,7 +852,7 @@ bool pm_wakeup_pending(void)
                ret = (cnt != saved_count || inpr > 0);
                events_check_enabled = !ret;
        }
-       spin_unlock_irqrestore(&events_lock, flags);
+       raw_spin_unlock_irqrestore(&events_lock, flags);
 
        if (ret) {
                pr_info("PM: Wakeup pending, aborting suspend\n");
@@ -941,13 +941,13 @@ bool pm_save_wakeup_count(unsigned int count)
        unsigned long flags;
 
        events_check_enabled = false;
-       spin_lock_irqsave(&events_lock, flags);
+       raw_spin_lock_irqsave(&events_lock, flags);
        split_counters(&cnt, &inpr);
        if (cnt == count && inpr == 0) {
                saved_count = count;
                events_check_enabled = true;
        }
-       spin_unlock_irqrestore(&events_lock, flags);
+       raw_spin_unlock_irqrestore(&events_lock, flags);
        return events_check_enabled;
 }
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2d7178f7754e..c1cf87718c2e 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -60,7 +60,6 @@ struct brd_device {
 /*
  * Look up and return a brd's page for a given sector.
  */
-static DEFINE_MUTEX(brd_mutex);
 static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 {
        pgoff_t idx;
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 5b8992beffec..40345483a022 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -116,12 +116,20 @@ ssize_t zcomp_available_show(const char *comp, char *buf)
 
 struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
 {
-       return *get_cpu_ptr(comp->stream);
+       struct zcomp_strm *zstrm;
+
+       zstrm = *get_local_ptr(comp->stream);
+       spin_lock(&zstrm->zcomp_lock);
+       return zstrm;
 }
 
 void zcomp_stream_put(struct zcomp *comp)
 {
-       put_cpu_ptr(comp->stream);
+       struct zcomp_strm *zstrm;
+
+       zstrm = *this_cpu_ptr(comp->stream);
+       spin_unlock(&zstrm->zcomp_lock);
+       put_local_ptr(zstrm);
 }
 
 int zcomp_compress(struct zcomp_strm *zstrm,
@@ -171,6 +179,7 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
                pr_err("Can't allocate a compression stream\n");
                return -ENOMEM;
        }
+       spin_lock_init(&zstrm->zcomp_lock);
        *per_cpu_ptr(comp->stream, cpu) = zstrm;
        return 0;
 }
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 41c1002a7d7d..d424eafcbf8e 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -14,6 +14,7 @@ struct zcomp_strm {
        /* compression/decompression buffer */
        void *buffer;
        struct crypto_comp *tfm;
+       spinlock_t zcomp_lock;
 };
 
 /* dynamic per-device compression frontend */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 1e2648e4c286..c5d61209eb05 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -761,6 +761,30 @@ static DEVICE_ATTR_RO(io_stat);
 static DEVICE_ATTR_RO(mm_stat);
 static DEVICE_ATTR_RO(debug_stat);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages)
+{
+       size_t index;
+
+       for (index = 0; index < num_pages; index++)
+               spin_lock_init(&zram->table[index].lock);
+}
+
+static void zram_slot_lock(struct zram *zram, u32 index)
+{
+       spin_lock(&zram->table[index].lock);
+       __set_bit(ZRAM_ACCESS, &zram->table[index].value);
+}
+
+static void zram_slot_unlock(struct zram *zram, u32 index)
+{
+       __clear_bit(ZRAM_ACCESS, &zram->table[index].value);
+       spin_unlock(&zram->table[index].lock);
+}
+
+#else
+static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { }
+
 static void zram_slot_lock(struct zram *zram, u32 index)
 {
        bit_spin_lock(ZRAM_ACCESS, &zram->table[index].value);
@@ -770,6 +794,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index)
 {
        bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
 }
+#endif
 
 static void zram_meta_free(struct zram *zram, u64 disksize)
 {
@@ -799,6 +824,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize)
                return false;
        }
 
+       zram_meta_init_table_locks(zram, num_pages);
        return true;
 }
 
@@ -850,6 +876,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
        unsigned long handle;
        unsigned int size;
        void *src, *dst;
+       struct zcomp_strm *zstrm;
 
        if (zram_wb_enabled(zram)) {
                zram_slot_lock(zram, index);
@@ -884,6 +911,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 
        size = zram_get_obj_size(zram, index);
 
+       zstrm = zcomp_stream_get(zram->comp);
        src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
        if (size == PAGE_SIZE) {
                dst = kmap_atomic(page);
@@ -891,14 +919,13 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
                kunmap_atomic(dst);
                ret = 0;
        } else {
-               struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
 
                dst = kmap_atomic(page);
                ret = zcomp_decompress(zstrm, src, size, dst);
                kunmap_atomic(dst);
-               zcomp_stream_put(zram->comp);
        }
        zs_unmap_object(zram->mem_pool, handle);
+       zcomp_stream_put(zram->comp);
        zram_slot_unlock(zram, index);
 
        /* Should NEVER happen. Return bio error if it does. */
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 31762db861e3..a417c96b8f3f 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -77,6 +77,9 @@ struct zram_table_entry {
                unsigned long element;
        };
        unsigned long value;
+#ifdef CONFIG_PREEMPT_RT_BASE
+       spinlock_t lock;
+#endif
 };
 
 struct zram_stats {
diff --git a/drivers/char/random.c b/drivers/char/random.c
index ea4dbfa30657..c72a7f0b4494 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -265,6 +265,7 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/locallock.h>
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
@@ -856,7 +857,7 @@ static int crng_fast_load(const char *cp, size_t len)
                invalidate_batched_entropy();
                crng_init = 1;
                wake_up_interruptible(&crng_init_wait);
-               pr_notice("random: fast init done\n");
+               /* pr_notice("random: fast init done\n"); */
        }
        return 1;
 }
@@ -941,17 +942,21 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
                crng_init = 2;
                process_random_ready_list();
                wake_up_interruptible(&crng_init_wait);
-               pr_notice("random: crng init done\n");
+               /* pr_notice("random: crng init done\n"); */
                if (unseeded_warning.missed) {
+#if 0
                        pr_notice("random: %d get_random_xx warning(s) missed "
                                  "due to ratelimiting\n",
                                  unseeded_warning.missed);
+#endif
                        unseeded_warning.missed = 0;
                }
                if (urandom_warning.missed) {
+#if 0
                        pr_notice("random: %d urandom warning(s) missed "
                                  "due to ratelimiting\n",
                                  urandom_warning.missed);
+#endif
                        urandom_warning.missed = 0;
                }
        }
@@ -1122,8 +1127,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
        } sample;
        long delta, delta2, delta3;
 
-       preempt_disable();
-
        sample.jiffies = jiffies;
        sample.cycles = random_get_entropy();
        sample.num = num;
@@ -1164,7 +1167,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
                 */
                credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
        }
-       preempt_enable();
 }
 
 void add_input_randomness(unsigned int type, unsigned int code,
@@ -1221,28 +1223,27 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
        return *ptr;
 }
 
-void add_interrupt_randomness(int irq, int irq_flags)
+void add_interrupt_randomness(int irq, int irq_flags, __u64 ip)
 {
        struct entropy_store    *r;
        struct fast_pool        *fast_pool = this_cpu_ptr(&irq_randomness);
-       struct pt_regs          *regs = get_irq_regs();
        unsigned long           now = jiffies;
        cycles_t                cycles = random_get_entropy();
        __u32                   c_high, j_high;
-       __u64                   ip;
        unsigned long           seed;
        int                     credit = 0;
 
        if (cycles == 0)
-               cycles = get_reg(fast_pool, regs);
+               cycles = get_reg(fast_pool, NULL);
        c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
        j_high = (sizeof(now) > 4) ? now >> 32 : 0;
        fast_pool->pool[0] ^= cycles ^ j_high ^ irq;
        fast_pool->pool[1] ^= now ^ c_high;
-       ip = regs ? instruction_pointer(regs) : _RET_IP_;
+       if (!ip)
+               ip = _RET_IP_;
        fast_pool->pool[2] ^= ip;
        fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
-               get_reg(fast_pool, regs);
+               get_reg(fast_pool, NULL);
 
        fast_mix(fast_pool);
        add_interrupt_bench(cycles);
@@ -2200,6 +2201,7 @@ static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_
  * at any point prior.
  */
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64);
+static DEFINE_LOCAL_IRQ_LOCK(batched_entropy_u64_lock);
 u64 get_random_u64(void)
 {
        u64 ret;
@@ -2220,7 +2222,7 @@ u64 get_random_u64(void)
        warn_unseeded_randomness(&previous);
 
        use_lock = READ_ONCE(crng_init) < 2;
-       batch = &get_cpu_var(batched_entropy_u64);
+       batch = &get_locked_var(batched_entropy_u64_lock, batched_entropy_u64);
        if (use_lock)
                read_lock_irqsave(&batched_entropy_reset_lock, flags);
        if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
@@ -2230,12 +2232,13 @@ u64 get_random_u64(void)
        ret = batch->entropy_u64[batch->position++];
        if (use_lock)
                read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
-       put_cpu_var(batched_entropy_u64);
+       put_locked_var(batched_entropy_u64_lock, batched_entropy_u64);
        return ret;
 }
 EXPORT_SYMBOL(get_random_u64);
 
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32);
+static DEFINE_LOCAL_IRQ_LOCK(batched_entropy_u32_lock);
 u32 get_random_u32(void)
 {
        u32 ret;
@@ -2250,7 +2253,7 @@ u32 get_random_u32(void)
        warn_unseeded_randomness(&previous);
 
        use_lock = READ_ONCE(crng_init) < 2;
-       batch = &get_cpu_var(batched_entropy_u32);
+       batch = &get_locked_var(batched_entropy_u32_lock, batched_entropy_u32);
        if (use_lock)
                read_lock_irqsave(&batched_entropy_reset_lock, flags);
        if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
@@ -2260,7 +2263,7 @@ u32 get_random_u32(void)
        ret = batch->entropy_u32[batch->position++];
        if (use_lock)
                read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
-       put_cpu_var(batched_entropy_u32);
+       put_locked_var(batched_entropy_u32_lock, batched_entropy_u32);
        return ret;
 }
 EXPORT_SYMBOL(get_random_u32);
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 50b59a69dc33..cbdb0a6c5337 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -52,6 +52,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da
        return container_of(data, struct tpm_tis_tcg_phy, priv);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * Flushes previous write operations to chip so that a subsequent
+ * ioread*()s won't stall a cpu.
+ */
+static inline void tpm_tis_flush(void __iomem *iobase)
+{
+       ioread8(iobase + TPM_ACCESS(0));
+}
+#else
+#define tpm_tis_flush(iobase) do { } while (0)
+#endif
+
+static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr)
+{
+       iowrite8(b, iobase + addr);
+       tpm_tis_flush(iobase);
+}
+
+static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr)
+{
+       iowrite32(b, iobase + addr);
+       tpm_tis_flush(iobase);
+}
+
 static bool interrupts = true;
 module_param(interrupts, bool, 0444);
 MODULE_PARM_DESC(interrupts, "Enable interrupts");
@@ -149,7 +174,7 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
        struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
        while (len--)
-               iowrite8(*value++, phy->iobase + addr);
+               tpm_tis_iowrite8(*value++, phy->iobase, addr);
 
        return 0;
 }
@@ -176,7 +201,7 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 {
        struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-       iowrite32(value, phy->iobase + addr);
+       tpm_tis_iowrite32(value, phy->iobase, addr);
 
        return 0;
 }
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 9de47d4d2d9e..05f4b88bb955 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -25,8 +25,7 @@
  *     this 32 bit free-running counter. the second channel is not used.
  *
  *   - The third channel may be used to provide a 16-bit clockevent
- *     source, used in either periodic or oneshot mode.  This runs
- *     at 32 KiHZ, and can handle delays of up to two seconds.
+ *     source, used in either periodic or oneshot mode.
  *
  * A boot clocksource and clockevent source are also currently needed,
  * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so
@@ -126,6 +125,8 @@ static struct clocksource clksrc = {
 struct tc_clkevt_device {
        struct clock_event_device       clkevt;
        struct clk                      *clk;
+       bool                            clk_enabled;
+       u32                             freq;
        void __iomem                    *regs;
 };
 
@@ -134,15 +135,26 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt)
        return container_of(clkevt, struct tc_clkevt_device, clkevt);
 }
 
-/* For now, we always use the 32K clock ... this optimizes for NO_HZ,
- * because using one of the divided clocks would usually mean the
- * tick rate can never be less than several dozen Hz (vs 0.5 Hz).
- *
- * A divided clock could be good for high resolution timers, since
- * 30.5 usec resolution can seem "low".
- */
 static u32 timer_clock;
 
+static void tc_clk_disable(struct clock_event_device *d)
+{
+       struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+
+       clk_disable(tcd->clk);
+       tcd->clk_enabled = false;
+}
+
+static void tc_clk_enable(struct clock_event_device *d)
+{
+       struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+
+       if (tcd->clk_enabled)
+               return;
+       clk_enable(tcd->clk);
+       tcd->clk_enabled = true;
+}
+
 static int tc_shutdown(struct clock_event_device *d)
 {
        struct tc_clkevt_device *tcd = to_tc_clkevt(d);
@@ -150,8 +162,14 @@ static int tc_shutdown(struct clock_event_device *d)
 
        writel(0xff, regs + ATMEL_TC_REG(2, IDR));
        writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
+       return 0;
+}
+
+static int tc_shutdown_clk_off(struct clock_event_device *d)
+{
+       tc_shutdown(d);
        if (!clockevent_state_detached(d))
-               clk_disable(tcd->clk);
+               tc_clk_disable(d);
 
        return 0;
 }
@@ -164,9 +182,9 @@ static int tc_set_oneshot(struct clock_event_device *d)
        if (clockevent_state_oneshot(d) || clockevent_state_periodic(d))
                tc_shutdown(d);
 
-       clk_enable(tcd->clk);
+       tc_clk_enable(d);
 
-       /* slow clock, count up to RC, then irq and stop */
+       /* count up to RC, then irq and stop */
        writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE |
                     ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR));
        writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -186,12 +204,12 @@ static int tc_set_periodic(struct clock_event_device *d)
        /* By not making the gentime core emulate periodic mode on top
         * of oneshot, we get lower overhead and improved accuracy.
         */
-       clk_enable(tcd->clk);
+       tc_clk_enable(d);
 
-       /* slow clock, count up to RC, then irq and restart */
+       /* count up to RC, then irq and restart */
        writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
                     regs + ATMEL_TC_REG(2, CMR));
-       writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
+       writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
 
        /* Enable clock and interrupts on RC compare */
        writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -218,9 +236,13 @@ static struct tc_clkevt_device clkevt = {
                .features               = CLOCK_EVT_FEAT_PERIODIC |
                                          CLOCK_EVT_FEAT_ONESHOT,
                /* Should be lower than at91rm9200's system timer */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
                .rating                 = 125,
+#else
+               .rating                 = 200,
+#endif
                .set_next_event         = tc_next_event,
-               .set_state_shutdown     = tc_shutdown,
+               .set_state_shutdown     = tc_shutdown_clk_off,
                .set_state_periodic     = tc_set_periodic,
                .set_state_oneshot      = tc_set_oneshot,
        },
@@ -240,8 +262,9 @@ static irqreturn_t ch2_irq(int irq, void *handle)
        return IRQ_NONE;
 }
 
-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
+static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx)
 {
+       unsigned divisor = atmel_tc_divisors[divisor_idx];
        int ret;
        struct clk *t2_clk = tc->clk[2];
        int irq = tc->irq[2];
@@ -262,7 +285,11 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
        clkevt.regs = tc->regs;
        clkevt.clk = t2_clk;
 
-       timer_clock = clk32k_divisor_idx;
+       timer_clock = divisor_idx;
+       if (!divisor)
+               clkevt.freq = 32768;
+       else
+               clkevt.freq = clk_get_rate(t2_clk) / divisor;
 
        clkevt.clkevt.cpumask = cpumask_of(0);
 
@@ -273,7 +300,7 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
                return ret;
        }
 
-       clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff);
+       clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff);
 
        return ret;
 }
@@ -410,7 +437,11 @@ static int __init tcb_clksrc_init(void)
                goto err_disable_t1;
 
        /* channel 2:  periodic and oneshot timer support */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
        ret = setup_clkevents(tc, clk32k_divisor_idx);
+#else
+       ret = setup_clkevents(tc, best_divisor_idx);
+#endif
        if (ret)
                goto err_unregister_clksrc;
 
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index 2fab18fae4fc..98460c1bdec0 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/drivers/clocksource/timer-atmel-pit.c
@@ -46,6 +46,7 @@ struct pit_data {
        u32             cycle;
        u32             cnt;
        unsigned int    irq;
+       bool            irq_requested;
        struct clk      *mck;
 };
 
@@ -96,15 +97,29 @@ static int pit_clkevt_shutdown(struct clock_event_device *dev)
 
        /* disable irq, leaving the clocksource active */
        pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN);
+       if (data->irq_requested) {
+               free_irq(data->irq, data);
+               data->irq_requested = false;
+       }
        return 0;
 }
 
+static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id);
 /*
  * Clockevent device:  interrupts every 1/HZ (== pit_cycles * MCK/16)
  */
 static int pit_clkevt_set_periodic(struct clock_event_device *dev)
 {
        struct pit_data *data = clkevt_to_pit_data(dev);
+       int ret;
+
+       ret = request_irq(data->irq, at91sam926x_pit_interrupt,
+                         IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+                         "at91_tick", data);
+       if (ret)
+               panic(pr_fmt("Unable to setup IRQ\n"));
+
+       data->irq_requested = true;
 
        /* update clocksource counter */
        data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR));
@@ -233,16 +248,6 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
                goto exit;
        }
 
-       /* Set up irq handler */
-       ret = request_irq(data->irq, at91sam926x_pit_interrupt,
-                         IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
-                         "at91_tick", data);
-       if (ret) {
-               pr_err("Unable to setup IRQ\n");
-               clocksource_unregister(&data->clksrc);
-               goto exit;
-       }
-
        /* Set up and register clockevents */
        data->clkevt.name = "pit";
        data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC;
diff --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c
index d2e660f475af..c63b96cfc23e 100644
--- a/drivers/clocksource/timer-atmel-st.c
+++ b/drivers/clocksource/timer-atmel-st.c
@@ -115,18 +115,29 @@ static void clkdev32k_disable_and_flush_irq(void)
        last_crtr = read_CRTR();
 }
 
+static int atmel_st_irq;
+
 static int clkevt32k_shutdown(struct clock_event_device *evt)
 {
        clkdev32k_disable_and_flush_irq();
        irqmask = 0;
        regmap_write(regmap_st, AT91_ST_IER, irqmask);
+       free_irq(atmel_st_irq, regmap_st);
        return 0;
 }
 
 static int clkevt32k_set_oneshot(struct clock_event_device *dev)
 {
+       int ret;
+
        clkdev32k_disable_and_flush_irq();
 
+       ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
+                         IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+                         "at91_tick", regmap_st);
+       if (ret)
+               panic(pr_fmt("Unable to setup IRQ\n"));
+
        /*
         * ALM for oneshot irqs, set by next_event()
         * before 32 seconds have passed.
@@ -139,8 +150,16 @@ static int clkevt32k_set_oneshot(struct clock_event_device *dev)
 
 static int clkevt32k_set_periodic(struct clock_event_device *dev)
 {
+       int ret;
+
        clkdev32k_disable_and_flush_irq();
 
+       ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
+                         IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+                         "at91_tick", regmap_st);
+       if (ret)
+               panic(pr_fmt("Unable to setup IRQ\n"));
+
        /* PIT for periodic irqs; fixed rate of 1/HZ */
        irqmask = AT91_ST_PITS;
        regmap_write(regmap_st, AT91_ST_PIMR, timer_latch);
@@ -198,7 +217,7 @@ static int __init atmel_st_timer_init(struct device_node *node)
 {
        struct clk *sclk;
        unsigned int sclk_rate, val;
-       int irq, ret;
+       int ret;
 
        regmap_st = syscon_node_to_regmap(node);
        if (IS_ERR(regmap_st)) {
@@ -212,21 +231,12 @@ static int __init atmel_st_timer_init(struct device_node *node)
        regmap_read(regmap_st, AT91_ST_SR, &val);
 
        /* Get the interrupts property */
-       irq  = irq_of_parse_and_map(node, 0);
-       if (!irq) {
+       atmel_st_irq  = irq_of_parse_and_map(node, 0);
+       if (!atmel_st_irq) {
                pr_err("Unable to get IRQ from DT\n");
                return -EINVAL;
        }
 
-       /* Make IRQs happen for the system timer */
-       ret = request_irq(irq, at91rm9200_timer_interrupt,
-                         IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
-                         "at91_tick", regmap_st);
-       if (ret) {
-               pr_err("Unable to setup IRQ\n");
-               return ret;
-       }
-
        sclk = of_clk_get(node, 0);
        if (IS_ERR(sclk)) {
                pr_err("Unable to get slow clock\n");
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index a782ce87715c..19d265948526 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -32,6 +32,7 @@
 #include <linux/pid_namespace.h>
 
 #include <linux/cn_proc.h>
+#include <linux/locallock.h>
 
 /*
  * Size of a cn_msg followed by a proc_event structure.  Since the
@@ -54,10 +55,11 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
 
 /* proc_event_counts is used as the sequence number of the netlink message */
 static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
+static DEFINE_LOCAL_IRQ_LOCK(send_msg_lock);
 
 static inline void send_msg(struct cn_msg *msg)
 {
-       preempt_disable();
+       local_lock(send_msg_lock);
 
        msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
        ((struct proc_event *)msg->data)->cpu = smp_processor_id();
@@ -70,7 +72,7 @@ static inline void send_msg(struct cn_msg *msg)
         */
        cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
 
-       preempt_enable();
+       local_unlock(send_msg_lock);
 }
 
 void proc_fork_connector(struct task_struct *task)
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 35f71825b7f3..bb4a6160d0f7 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -125,7 +125,7 @@ config X86_POWERNOW_K7_ACPI
 
 config X86_POWERNOW_K8
        tristate "AMD Opteron/Athlon64 PowerNow!"
-       depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
+       depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE
        help
          This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
          Support for K10 and newer processors is now in acpi-cpufreq.
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index c3eefa126e3b..47093745a53c 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -74,7 +74,7 @@ static unsigned long *efi_tables[] = {
        &efi.mem_attr_table,
 };
 
-static bool disable_runtime;
+static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT_BASE);
 static int __init setup_noefi(char *arg)
 {
        disable_runtime = true;
@@ -100,6 +100,9 @@ static int __init parse_efi_cmdline(char *str)
        if (parse_option_str(str, "noruntime"))
                disable_runtime = true;
 
+       if (parse_option_str(str, "runtime"))
+               disable_runtime = false;
+
        return 0;
 }
 early_param("efi", parse_efi_cmdline);
diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.c b/drivers/gpu/drm/i915/i915_gem_timeline.c
index c597ce277a04..c1108d3921f8 100644
--- a/drivers/gpu/drm/i915/i915_gem_timeline.c
+++ b/drivers/gpu/drm/i915/i915_gem_timeline.c
@@ -33,11 +33,8 @@ static void __intel_timeline_init(struct intel_timeline *tl,
 {
        tl->fence_context = context;
        tl->common = parent;
-#ifdef CONFIG_DEBUG_SPINLOCK
-       __raw_spin_lock_init(&tl->lock.rlock, lockname, lockclass);
-#else
        spin_lock_init(&tl->lock);
-#endif
+       lockdep_set_class_and_name(&tl->lock, lockclass, lockname);
        init_request_active(&tl->last_request, NULL);
        INIT_LIST_HEAD(&tl->requests);
        i915_syncmap_init(&tl->sync);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 20a471ad0ad2..5d34d48a8b7b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -867,6 +867,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
        spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
        /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+       preempt_disable_rt();
 
        /* Get optional system timestamp before query. */
        if (stime)
@@ -918,6 +919,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
                *etime = ktime_get();
 
        /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+       preempt_enable_rt();
 
        spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 41e31a454604..7e0cadf51b31 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -36,6 +36,7 @@
 #include <drm/drm_rect.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_plane_helper.h>
+#include <linux/locallock.h>
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
 #include <drm/i915_drm.h>
@@ -67,7 +68,7 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 }
 
 #define VBLANK_EVASION_TIME_US 100
-
+static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock);
 /**
  * intel_pipe_update_start() - start update of a set of display registers
  * @crtc: the crtc of which the registers are going to be updated
@@ -102,7 +103,7 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
                                                      VBLANK_EVASION_TIME_US);
        max = vblank_start - 1;
 
-       local_irq_disable();
+       local_lock_irq(pipe_update_lock);
 
        if (min <= 0 || max <= 0)
                return;
@@ -132,11 +133,11 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
                        break;
                }
 
-               local_irq_enable();
+               local_unlock_irq(pipe_update_lock);
 
                timeout = schedule_timeout(timeout);
 
-               local_irq_disable();
+               local_lock_irq(pipe_update_lock);
        }
 
        finish_wait(wq, &wait);
@@ -201,7 +202,7 @@ void intel_pipe_update_end(struct intel_crtc *crtc)
                crtc->base.state->event = NULL;
        }
 
-       local_irq_enable();
+       local_unlock_irq(pipe_update_lock);
 
        if (intel_vgpu_active(dev_priv))
                return;
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index ddfe91efa61e..3157bcf6428f 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1839,6 +1839,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
        struct radeon_device *rdev = dev->dev_private;
 
        /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+       preempt_disable_rt();
 
        /* Get optional system timestamp before query. */
        if (stime)
@@ -1931,6 +1932,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
                *etime = ktime_get();
 
        /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+       preempt_enable_rt();
 
        /* Decode into vertical and horizontal scanout position. */
        *vpos = position & 0x1fff;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 49569f8fe038..a3608cd52805 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -30,6 +30,7 @@
 #include <linux/atomic.h>
 #include <linux/hyperv.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 
 /*
  * Timeout for services such as KVP and fcopy.
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 2cd134dd94d2..cedf225d4182 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -966,6 +966,8 @@ static void vmbus_isr(void)
        void *page_addr = hv_cpu->synic_event_page;
        struct hv_message *msg;
        union hv_synic_event_flags *event;
+       struct pt_regs *regs = get_irq_regs();
+       u64 ip = regs ? instruction_pointer(regs) : 0;
        bool handled = false;
 
        if (unlikely(page_addr == NULL))
@@ -1009,7 +1011,7 @@ static void vmbus_isr(void)
                        tasklet_schedule(&hv_cpu->msg_dpc);
        }
 
-       add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
+       add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, ip);
 }
 
 
diff --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c
index 36f76e28a0bf..394f142f90c7 100644
--- a/drivers/ide/alim15x3.c
+++ b/drivers/ide/alim15x3.c
@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct pci_dev *dev)
 
        isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
 
        if (m5229_revision < 0xC2) {
                /*
@@ -325,7 +325,7 @@ static int init_chipset_ali15x3(struct pci_dev *dev)
        }
        pci_dev_put(north);
        pci_dev_put(isa_dev);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
        return 0;
 }
 
diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
index 4b5dc0162e67..590cc7d64622 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -1236,7 +1236,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
 
        dma_old = inb(base + 2);
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
 
        dma_new = dma_old;
        pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma);
@@ -1247,7 +1247,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
        if (dma_new != dma_old)
                outb(dma_new, base + 2);
 
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 
        printk(KERN_INFO "    %s: BM-DMA at 0x%04lx-0x%04lx\n",
                         hwif->name, base, base + 7);
diff --git a/drivers/ide/ide-io-std.c b/drivers/ide/ide-io-std.c
index 19763977568c..4169433faab5 100644
--- a/drivers/ide/ide-io-std.c
+++ b/drivers/ide/ide-io-std.c
@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
                unsigned long uninitialized_var(flags);
 
                if ((io_32bit & 2) && !mmio) {
-                       local_irq_save(flags);
+                       local_irq_save_nort(flags);
                        ata_vlb_sync(io_ports->nsect_addr);
                }
 
@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
                        insl(data_addr, buf, words);
 
                if ((io_32bit & 2) && !mmio)
-                       local_irq_restore(flags);
+                       local_irq_restore_nort(flags);
 
                if (((len + 1) & 3) < 2)
                        return;
@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
                unsigned long uninitialized_var(flags);
 
                if ((io_32bit & 2) && !mmio) {
-                       local_irq_save(flags);
+                       local_irq_save_nort(flags);
                        ata_vlb_sync(io_ports->nsect_addr);
                }
 
@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
                        outsl(data_addr, buf, words);
 
                if ((io_32bit & 2) && !mmio)
-                       local_irq_restore(flags);
+                       local_irq_restore_nort(flags);
 
                if (((len + 1) & 3) < 2)
                        return;
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 3a234701d92c..420e4e645856 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -660,7 +660,7 @@ void ide_timer_expiry (unsigned long data)
                /* disable_irq_nosync ?? */
                disable_irq(hwif->irq);
                /* local CPU only, as if we were handling an interrupt */
-               local_irq_disable();
+               local_irq_disable_nort();
                if (hwif->polling) {
                        startstop = handler(drive);
                } else if (drive_is_ready(drive)) {
diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
index 210a0887dd29..7bf05b6147e8 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, u8 good, u8 bad,
                                if ((stat & ATA_BUSY) == 0)
                                        break;
 
-                               local_irq_restore(flags);
+                               local_irq_restore_nort(flags);
                                *rstat = stat;
                                return -EBUSY;
                        }
                }
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
        }
        /*
         * Allow status to settle, then read it again.
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index eaf39e5db08b..be4c941eaa83 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *drive, u8 cmd, u16 *id)
        int bswap = 1;
 
        /* local CPU only; some systems need this */
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        /* read 512 bytes of id info */
        hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 
        drive->dev_flags |= IDE_DFLAG_ID_READ;
 #ifdef DEBUG
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index 4efe4c6e956c..7eae3aa1def7 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -251,7 +251,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
 
                page_is_high = PageHighMem(page);
                if (page_is_high)
-                       local_irq_save(flags);
+                       local_irq_save_nort(flags);
 
                buf = kmap_atomic(page) + offset;
 
@@ -272,7 +272,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
                kunmap_atomic(buf);
 
                if (page_is_high)
-                       local_irq_restore(flags);
+                       local_irq_restore_nort(flags);
 
                len -= nr_bytes;
        }
@@ -415,7 +415,7 @@ static ide_startstop_t pre_task_out_intr(ide_drive_t *drive,
        }
 
        if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
-               local_irq_disable();
+               local_irq_disable_nort();
 
        ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);
 
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index b197e925fe36..95ac319c8e69 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -593,7 +593,7 @@ int hfi1_get_proc_affinity(int node)
        struct hfi1_affinity_node *entry;
        cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask;
        const struct cpumask *node_mask,
-               *proc_mask = &current->cpus_allowed;
+               *proc_mask = current->cpus_ptr;
        struct hfi1_affinity_node_list *affinity = &node_affinity;
        struct cpu_mask_set *set = &affinity->proc;
 
@@ -601,7 +601,7 @@ int hfi1_get_proc_affinity(int node)
         * check whether process/context affinity has already
         * been set
         */
-       if (cpumask_weight(proc_mask) == 1) {
+       if (current->nr_cpus_allowed == 1) {
                hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl",
                          current->pid, current->comm,
                          cpumask_pr_args(proc_mask));
@@ -612,7 +612,7 @@ int hfi1_get_proc_affinity(int node)
                cpu = cpumask_first(proc_mask);
                cpumask_set_cpu(cpu, &set->used);
                goto done;
-       } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) {
+       } else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) {
                hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
                          current->pid, current->comm,
                          cpumask_pr_args(proc_mask));
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 6781bcdb10b3..d069ad261572 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -856,14 +856,13 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
 {
        struct sdma_rht_node *rht_node;
        struct sdma_engine *sde = NULL;
-       const struct cpumask *current_mask = &current->cpus_allowed;
        unsigned long cpu_id;
 
        /*
         * To ensure that always the same sdma engine(s) will be
         * selected make sure the process is pinned to this CPU only.
         */
-       if (cpumask_weight(current_mask) != 1)
+       if (current->nr_cpus_allowed != 1)
                goto out;
 
        cpu_id = smp_processor_id();
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 40efc9151ec4..12924aad90cc 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -1167,7 +1167,7 @@ static unsigned int qib_poll(struct file *fp, struct poll_table_struct *pt)
 static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd)
 {
        struct qib_filedata *fd = fp->private_data;
-       const unsigned int weight = cpumask_weight(&current->cpus_allowed);
+       const unsigned int weight = current->nr_cpus_allowed;
        const struct cpumask *local_mask = cpumask_of_pcibus(dd->pcidev->bus);
        int local_cpu;
 
@@ -1648,9 +1648,8 @@ static int qib_assign_ctxt(struct file *fp, const struct qib_user_info *uinfo)
                ret = find_free_ctxt(i_minor - 1, fp, uinfo);
        else {
                int unit;
-               const unsigned int cpu = cpumask_first(&current->cpus_allowed);
-               const unsigned int weight =
-                       cpumask_weight(&current->cpus_allowed);
+               const unsigned int cpu = cpumask_first(current->cpus_ptr);
+               const unsigned int weight = current->nr_cpus_allowed;
 
                if (weight == 1 && !test_bit(cpu, qib_cpulist))
                        if (!find_hca(cpu, &unit) && unit >= 0)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 9b3f47ae2016..8327b598d909 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -898,7 +898,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 
        ipoib_dbg_mcast(priv, "restarting multicast task\n");
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        netif_addr_lock(dev);
        spin_lock(&priv->lock);
 
@@ -980,7 +980,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 
        spin_unlock(&priv->lock);
        netif_addr_unlock(dev);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 
        ipoib_mcast_remove_list(&remove_list);
 
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index cedc665364cd..4a4fdef151aa 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -91,13 +91,13 @@ static int gameport_measure_speed(struct gameport *gameport)
        tx = ~0;
 
        for (i = 0; i < 50; i++) {
-               local_irq_save(flags);
+               local_irq_save_nort(flags);
                t1 = ktime_get_ns();
                for (t = 0; t < 50; t++)
                        gameport_read(gameport);
                t2 = ktime_get_ns();
                t3 = ktime_get_ns();
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
                udelay(i * 10);
                t = (t2 - t1) - (t3 - t2);
                if (t < tx)
@@ -124,12 +124,12 @@ static int old_gameport_measure_speed(struct gameport *gameport)
        tx = 1 << 30;
 
        for(i = 0; i < 50; i++) {
-               local_irq_save(flags);
+               local_irq_save_nort(flags);
                GET_TIME(t1);
                for (t = 0; t < 50; t++) gameport_read(gameport);
                GET_TIME(t2);
                GET_TIME(t3);
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
                udelay(i * 10);
                if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t;
        }
@@ -148,11 +148,11 @@ static int old_gameport_measure_speed(struct gameport *gameport)
        tx = 1 << 30;
 
        for(i = 0; i < 50; i++) {
-               local_irq_save(flags);
+               local_irq_save_nort(flags);
                t1 = rdtsc();
                for (t = 0; t < 50; t++) gameport_read(gameport);
                t2 = rdtsc();
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
                udelay(i * 10);
                if (t2 - t1 < tx) tx = t2 - t1;
        }
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index efa6cd2500b9..7d9d41f803d1 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -81,11 +81,12 @@
  */
 #define AMD_IOMMU_PGSIZES      ((~0xFFFUL) & ~(2ULL << 38))
 
-static DEFINE_RWLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(pd_bitmap_lock);
+static DEFINE_SPINLOCK(iommu_table_lock);
 
 /* List of all available dev_data structures */
-static LIST_HEAD(dev_data_list);
-static DEFINE_SPINLOCK(dev_data_list_lock);
+static LLIST_HEAD(dev_data_list);
 
 LIST_HEAD(ioapic_map);
 LIST_HEAD(hpet_map);
@@ -204,40 +205,33 @@ static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
        struct iommu_dev_data *dev_data;
-       unsigned long flags;
 
        dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
        if (!dev_data)
                return NULL;
 
        dev_data->devid = devid;
-
-       spin_lock_irqsave(&dev_data_list_lock, flags);
-       list_add_tail(&dev_data->dev_data_list, &dev_data_list);
-       spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
        ratelimit_default_init(&dev_data->rs);
 
+       llist_add(&dev_data->dev_data_list, &dev_data_list);
        return dev_data;
 }
 
 static struct iommu_dev_data *search_dev_data(u16 devid)
 {
        struct iommu_dev_data *dev_data;
-       unsigned long flags;
+       struct llist_node *node;
+
+       if (llist_empty(&dev_data_list))
+               return NULL;
 
-       spin_lock_irqsave(&dev_data_list_lock, flags);
-       list_for_each_entry(dev_data, &dev_data_list, dev_data_list) {
+       node = dev_data_list.first;
+       llist_for_each_entry(dev_data, node, dev_data_list) {
                if (dev_data->devid == devid)
-                       goto out_unlock;
+                       return dev_data;
        }
 
-       dev_data = NULL;
-
-out_unlock:
-       spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
-       return dev_data;
+       return NULL;
 }
 
 static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -1062,9 +1056,9 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu,
        unsigned long flags;
        int ret;
 
-       spin_lock_irqsave(&iommu->lock, flags);
+       raw_spin_lock_irqsave(&iommu->lock, flags);
        ret = __iommu_queue_command_sync(iommu, cmd, sync);
-       spin_unlock_irqrestore(&iommu->lock, flags);
+       raw_spin_unlock_irqrestore(&iommu->lock, flags);
 
        return ret;
 }
@@ -1090,7 +1084,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
        build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
 
-       spin_lock_irqsave(&iommu->lock, flags);
+       raw_spin_lock_irqsave(&iommu->lock, flags);
 
        iommu->cmd_sem = 0;
 
@@ -1101,7 +1095,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
        ret = wait_on_sem(&iommu->cmd_sem);
 
 out_unlock:
-       spin_unlock_irqrestore(&iommu->lock, flags);
+       raw_spin_unlock_irqrestore(&iommu->lock, flags);
 
        return ret;
 }
@@ -1610,29 +1604,26 @@ static void del_domain_from_list(struct protection_domain *domain)
 
 static u16 domain_id_alloc(void)
 {
-       unsigned long flags;
        int id;
 
-       write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+       spin_lock(&pd_bitmap_lock);
        id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
        BUG_ON(id == 0);
        if (id > 0 && id < MAX_DOMAIN_ID)
                __set_bit(id, amd_iommu_pd_alloc_bitmap);
        else
                id = 0;
-       write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+       spin_unlock(&pd_bitmap_lock);
 
        return id;
 }
 
 static void domain_id_free(int id)
 {
-       unsigned long flags;
-
-       write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+       spin_lock(&pd_bitmap_lock);
        if (id > 0 && id < MAX_DOMAIN_ID)
                __clear_bit(id, amd_iommu_pd_alloc_bitmap);
-       write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+       spin_unlock(&pd_bitmap_lock);
 }
 
 #define DEFINE_FREE_PT_FN(LVL, FN)                             \
@@ -1952,10 +1943,10 @@ static int __attach_device(struct iommu_dev_data *dev_data,
        int ret;
 
        /*
-        * Must be called with IRQs disabled. Warn here to detect early
-        * when its not.
+        * Must be called with IRQs disabled on a non RT kernel. Warn here to
+        * detect early when its not.
         */
-       WARN_ON(!irqs_disabled());
+       WARN_ON_NONRT(!irqs_disabled());
 
        /* lock domain */
        spin_lock(&domain->lock);
@@ -2101,9 +2092,9 @@ static int attach_device(struct device *dev,
        }
 
 skip_ats_check:
-       write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+       spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
        ret = __attach_device(dev_data, domain);
-       write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+       spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
        /*
         * We might boot into a crash-kernel here. The crashed kernel
@@ -2123,10 +2114,10 @@ static void __detach_device(struct iommu_dev_data *dev_data)
        struct protection_domain *domain;
 
        /*
-        * Must be called with IRQs disabled. Warn here to detect early
-        * when its not.
+        * Must be called with IRQs disabled on a non RT kernel. Warn here to
+        * detect early when its not.
         */
-       WARN_ON(!irqs_disabled());
+       WARN_ON_NONRT(!irqs_disabled());
 
        if (WARN_ON(!dev_data->domain))
                return;
@@ -2153,9 +2144,9 @@ static void detach_device(struct device *dev)
        domain   = dev_data->domain;
 
        /* lock device table */
-       write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+       spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
        __detach_device(dev_data);
-       write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+       spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
        if (!dev_is_pci(dev))
                return;
@@ -2819,7 +2810,7 @@ static void cleanup_domain(struct protection_domain *domain)
        struct iommu_dev_data *entry;
        unsigned long flags;
 
-       write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+       spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
 
        while (!list_empty(&domain->dev_list)) {
                entry = list_first_entry(&domain->dev_list,
@@ -2827,7 +2818,7 @@ static void cleanup_domain(struct protection_domain *domain)
                __detach_device(entry);
        }
 
-       write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+       spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 }
 
 static void protection_domain_free(struct protection_domain *domain)
@@ -3594,14 +3585,62 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
        amd_iommu_dev_table[devid].data[2] = dte;
 }
 
-static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
+static struct irq_remap_table *get_irq_table(u16 devid)
+{
+       struct irq_remap_table *table;
+
+       if (WARN_ONCE(!amd_iommu_rlookup_table[devid],
+                     "%s: no iommu for devid %x\n", __func__, devid))
+               return NULL;
+
+       table = irq_lookup_table[devid];
+       if (WARN_ONCE(!table, "%s: no table for devid %x\n", __func__, devid))
+               return NULL;
+
+       return table;
+}
+
+static struct irq_remap_table *__alloc_irq_table(void)
+{
+       struct irq_remap_table *table;
+
+       table = kzalloc(sizeof(*table), GFP_KERNEL);
+       if (!table)
+               return NULL;
+
+       table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL);
+       if (!table->table) {
+               kfree(table);
+               return NULL;
+       }
+       raw_spin_lock_init(&table->lock);
+
+       if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+               memset(table->table, 0,
+                      MAX_IRQS_PER_TABLE * sizeof(u32));
+       else
+               memset(table->table, 0,
+                      (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
+       return table;
+}
+
+static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
+                                 struct irq_remap_table *table)
+{
+       irq_lookup_table[devid] = table;
+       set_dte_irq_entry(devid, table);
+       iommu_flush_dte(iommu, devid);
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid)
 {
        struct irq_remap_table *table = NULL;
+       struct irq_remap_table *new_table = NULL;
        struct amd_iommu *iommu;
        unsigned long flags;
        u16 alias;
 
-       write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+       spin_lock_irqsave(&iommu_table_lock, flags);
 
        iommu = amd_iommu_rlookup_table[devid];
        if (!iommu)
@@ -3614,60 +3653,45 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
        alias = amd_iommu_alias_table[devid];
        table = irq_lookup_table[alias];
        if (table) {
-               irq_lookup_table[devid] = table;
-               set_dte_irq_entry(devid, table);
-               iommu_flush_dte(iommu, devid);
-               goto out;
+               set_remap_table_entry(iommu, devid, table);
+               goto out_wait;
        }
+       spin_unlock_irqrestore(&iommu_table_lock, flags);
 
        /* Nothing there yet, allocate new irq remapping table */
-       table = kzalloc(sizeof(*table), GFP_ATOMIC);
-       if (!table)
-               goto out_unlock;
-
-       /* Initialize table spin-lock */
-       spin_lock_init(&table->lock);
+       new_table = __alloc_irq_table();
+       if (!new_table)
+               return NULL;
 
-       if (ioapic)
-               /* Keep the first 32 indexes free for IOAPIC interrupts */
-               table->min_index = 32;
+       spin_lock_irqsave(&iommu_table_lock, flags);
 
-       table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_ATOMIC);
-       if (!table->table) {
-               kfree(table);
-               table = NULL;
+       table = irq_lookup_table[devid];
+       if (table)
                goto out_unlock;
-       }
-
-       if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
-               memset(table->table, 0,
-                      MAX_IRQS_PER_TABLE * sizeof(u32));
-       else
-               memset(table->table, 0,
-                      (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
 
-       if (ioapic) {
-               int i;
-
-               for (i = 0; i < 32; ++i)
-                       iommu->irte_ops->set_allocated(table, i);
+       table = irq_lookup_table[alias];
+       if (table) {
+               set_remap_table_entry(iommu, devid, table);
+               goto out_wait;
        }
 
-       irq_lookup_table[devid] = table;
-       set_dte_irq_entry(devid, table);
-       iommu_flush_dte(iommu, devid);
-       if (devid != alias) {
-               irq_lookup_table[alias] = table;
-               set_dte_irq_entry(alias, table);
-               iommu_flush_dte(iommu, alias);
-       }
+       table = new_table;
+       new_table = NULL;
 
-out:
+       set_remap_table_entry(iommu, devid, table);
+       if (devid != alias)
+               set_remap_table_entry(iommu, alias, table);
+
+out_wait:
        iommu_completion_wait(iommu);
 
 out_unlock:
-       write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+       spin_unlock_irqrestore(&iommu_table_lock, flags);
 
+       if (new_table) {
+               kmem_cache_free(amd_iommu_irq_cache, new_table->table);
+               kfree(new_table);
+       }
        return table;
 }
 
@@ -3681,11 +3705,11 @@ static int alloc_irq_index(u16 devid, int count)
        if (!iommu)
                return -ENODEV;
 
-       table = get_irq_table(devid, false);
+       table = alloc_irq_table(devid);
        if (!table)
                return -ENODEV;
 
-       spin_lock_irqsave(&table->lock, flags);
+       raw_spin_lock_irqsave(&table->lock, flags);
 
        /* Scan table for free entries */
        for (c = 0, index = table->min_index;
@@ -3708,7 +3732,7 @@ static int alloc_irq_index(u16 devid, int count)
        index = -ENOSPC;
 
 out:
-       spin_unlock_irqrestore(&table->lock, flags);
+       raw_spin_unlock_irqrestore(&table->lock, flags);
 
        return index;
 }
@@ -3725,11 +3749,11 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
        if (iommu == NULL)
                return -EINVAL;
 
-       table = get_irq_table(devid, false);
+       table = get_irq_table(devid);
        if (!table)
                return -ENOMEM;
 
-       spin_lock_irqsave(&table->lock, flags);
+       raw_spin_lock_irqsave(&table->lock, flags);
 
        entry = (struct irte_ga *)table->table;
        entry = &entry[index];
@@ -3740,7 +3764,7 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
        if (data)
                data->ref = entry;
 
-       spin_unlock_irqrestore(&table->lock, flags);
+       raw_spin_unlock_irqrestore(&table->lock, flags);
 
        iommu_flush_irt(iommu, devid);
        iommu_completion_wait(iommu);
@@ -3758,13 +3782,13 @@ static int modify_irte(u16 devid, int index, union irte *irte)
        if (iommu == NULL)
                return -EINVAL;
 
-       table = get_irq_table(devid, false);
+       table = get_irq_table(devid);
        if (!table)
                return -ENOMEM;
 
-       spin_lock_irqsave(&table->lock, flags);
+       raw_spin_lock_irqsave(&table->lock, flags);
        table->table[index] = irte->val;
-       spin_unlock_irqrestore(&table->lock, flags);
+       raw_spin_unlock_irqrestore(&table->lock, flags);
 
        iommu_flush_irt(iommu, devid);
        iommu_completion_wait(iommu);
@@ -3782,13 +3806,13 @@ static void free_irte(u16 devid, int index)
        if (iommu == NULL)
                return;
 
-       table = get_irq_table(devid, false);
+       table = get_irq_table(devid);
        if (!table)
                return;
 
-       spin_lock_irqsave(&table->lock, flags);
+       raw_spin_lock_irqsave(&table->lock, flags);
        iommu->irte_ops->clear_allocated(table, index);
-       spin_unlock_irqrestore(&table->lock, flags);
+       raw_spin_unlock_irqrestore(&table->lock, flags);
 
        iommu_flush_irt(iommu, devid);
        iommu_completion_wait(iommu);
@@ -3869,10 +3893,8 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
                                 u8 vector, u32 dest_apicid)
 {
        struct irte_ga *irte = (struct irte_ga *) entry;
-       struct iommu_dev_data *dev_data = search_dev_data(devid);
 
-       if (!dev_data || !dev_data->use_vapic ||
-           !irte->lo.fields_remap.guest_mode) {
+       if (!irte->lo.fields_remap.guest_mode) {
                irte->hi.fields.vector = vector;
                irte->lo.fields_remap.destination = dest_apicid;
                modify_irte_ga(devid, index, irte, NULL);
@@ -4078,7 +4100,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
        struct amd_ir_data *data = NULL;
        struct irq_cfg *cfg;
        int i, ret, devid;
-       int index = -1;
+       int index;
 
        if (!info)
                return -EINVAL;
@@ -4102,10 +4124,26 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
                return ret;
 
        if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
-               if (get_irq_table(devid, true))
+               struct irq_remap_table *table;
+               struct amd_iommu *iommu;
+
+               table = alloc_irq_table(devid);
+               if (table) {
+                       if (!table->min_index) {
+                               /*
+                                * Keep the first 32 indexes free for IOAPIC
+                                * interrupts.
+                                */
+                               table->min_index = 32;
+                               iommu = amd_iommu_rlookup_table[devid];
+                               for (i = 0; i < 32; ++i)
+                                       iommu->irte_ops->set_allocated(table, i);
+                       }
+                       WARN_ON(table->min_index != 32);
                        index = info->ioapic_pin;
-               else
-                       ret = -ENOMEM;
+               } else {
+                       index = -ENOMEM;
+               }
        } else {
                index = alloc_irq_index(devid, nr_irqs);
        }
@@ -4349,7 +4387,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 {
        unsigned long flags;
        struct amd_iommu *iommu;
-       struct irq_remap_table *irt;
+       struct irq_remap_table *table;
        struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
        int devid = ir_data->irq_2_irte.devid;
        struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -4363,11 +4401,11 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
        if (!iommu)
                return -ENODEV;
 
-       irt = get_irq_table(devid, false);
-       if (!irt)
+       table = get_irq_table(devid);
+       if (!table)
                return -ENODEV;
 
-       spin_lock_irqsave(&irt->lock, flags);
+       raw_spin_lock_irqsave(&table->lock, flags);
 
        if (ref->lo.fields_vapic.guest_mode) {
                if (cpu >= 0)
@@ -4376,7 +4414,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
                barrier();
        }
 
-       spin_unlock_irqrestore(&irt->lock, flags);
+       raw_spin_unlock_irqrestore(&table->lock, flags);
 
        iommu_flush_irt(iommu, devid);
        iommu_completion_wait(iommu);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6fe2d0346073..e3cd81b32a33 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1474,7 +1474,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 {
        int ret;
 
-       spin_lock_init(&iommu->lock);
+       raw_spin_lock_init(&iommu->lock);
 
        /* Add IOMMU to internal data structures */
        list_add_tail(&iommu->list, &amd_iommu_list);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index f6b24c7d8b70..16b1404da58c 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -406,7 +406,7 @@ extern bool amd_iommu_iotlb_sup;
 #define IRQ_TABLE_ALIGNMENT    128
 
 struct irq_remap_table {
-       spinlock_t lock;
+       raw_spinlock_t lock;
        unsigned min_index;
        u32 *table;
 };
@@ -488,7 +488,7 @@ struct amd_iommu {
        int index;
 
        /* locks the accesses to the hardware */
-       spinlock_t lock;
+       raw_spinlock_t lock;
 
        /* Pointer to PCI device of this IOMMU */
        struct pci_dev *dev;
@@ -625,7 +625,7 @@ struct devid_map {
  */
 struct iommu_dev_data {
        struct list_head list;            /* For domain->dev_list */
-       struct list_head dev_data_list;   /* For global dev_data_list */
+       struct llist_node dev_data_list;  /* For global dev_data_list */
        struct protection_domain *domain; /* Domain the device is bound to */
        u16 devid;                        /* PCI Device ID */
        u16 alias;                        /* Alias Device ID */
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 33edfa794ae9..b30900025c62 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -570,7 +570,7 @@ void queue_iova(struct iova_domain *iovad,
                unsigned long pfn, unsigned long pages,
                unsigned long data)
 {
-       struct iova_fq *fq = get_cpu_ptr(iovad->fq);
+       struct iova_fq *fq = raw_cpu_ptr(iovad->fq);
        unsigned long flags;
        unsigned idx;
 
@@ -600,8 +600,6 @@ void queue_iova(struct iova_domain *iovad,
        if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
                mod_timer(&iovad->fq_timer,
                          jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
-
-       put_cpu_ptr(iovad->fq);
 }
 EXPORT_SYMBOL_GPL(queue_iova);
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 2ea39a83737f..a3e23d0fc4af 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -148,7 +148,7 @@ static struct {
 } vpe_proxy;
 
 static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
@@ -165,6 +165,7 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock);
 static DEFINE_IDA(its_vpeid_ida);
 
 #define gic_data_rdist()               (raw_cpu_ptr(gic_rdists->rdist))
+#define gic_data_rdist_cpu(cpu)                (per_cpu_ptr(gic_rdists->rdist, cpu))
 #define gic_data_rdist_rd_base()       (gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()     (gic_data_rdist_rd_base() + SZ_128K)
 
@@ -1432,7 +1433,7 @@ static void its_free_prop_table(struct page *prop_page)
                   get_order(LPI_PROPBASE_SZ));
 }
 
-static int __init its_alloc_lpi_tables(void)
+static int __init its_alloc_lpi_prop_table(void)
 {
        phys_addr_t paddr;
 
@@ -1758,30 +1759,47 @@ static void its_free_pending_table(struct page *pt)
                   get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K)));
 }
 
-static void its_cpu_init_lpis(void)
+static int __init allocate_lpi_tables(void)
 {
-       void __iomem *rbase = gic_data_rdist_rd_base();
-       struct page *pend_page;
-       u64 val, tmp;
+       int err, cpu;
 
-       /* If we didn't allocate the pending table yet, do it now */
-       pend_page = gic_data_rdist()->pend_page;
-       if (!pend_page) {
-               phys_addr_t paddr;
+       err = its_alloc_lpi_prop_table();
+       if (err)
+               return err;
+
+       /*
+        * We allocate all the pending tables anyway, as we may have a
+        * mix of RDs that have had LPIs enabled, and some that
+        * don't. We'll free the unused ones as each CPU comes online.
+        */
+       for_each_possible_cpu(cpu) {
+               struct page *pend_page;
 
                pend_page = its_allocate_pending_table(GFP_NOWAIT);
                if (!pend_page) {
-                       pr_err("Failed to allocate PENDBASE for CPU%d\n",
-                              smp_processor_id());
-                       return;
+                       pr_err("Failed to allocate PENDBASE for CPU%d\n", cpu);
+                       return -ENOMEM;
                }
 
-               paddr = page_to_phys(pend_page);
-               pr_info("CPU%d: using LPI pending table @%pa\n",
-                       smp_processor_id(), &paddr);
-               gic_data_rdist()->pend_page = pend_page;
+               gic_data_rdist_cpu(cpu)->pend_page = pend_page;
        }
 
+       return 0;
+}
+
+static void its_cpu_init_lpis(void)
+{
+       void __iomem *rbase = gic_data_rdist_rd_base();
+       struct page *pend_page;
+       phys_addr_t paddr;
+       u64 val, tmp;
+
+       if (gic_data_rdist()->lpi_enabled)
+               return;
+
+       pend_page = gic_data_rdist()->pend_page;
+       paddr = page_to_phys(pend_page);
+
        /* Disable LPIs */
        val = readl_relaxed(rbase + GICR_CTLR);
        val &= ~GICR_CTLR_ENABLE_LPIS;
@@ -1843,6 +1861,10 @@ static void its_cpu_init_lpis(void)
 
        /* Make sure the GIC has seen the above */
        dsb(sy);
+       gic_data_rdist()->lpi_enabled = true;
+       pr_info("GICv3: CPU%d: using LPI pending table @%pa\n",
+               smp_processor_id(),
+               &paddr);
 }
 
 static void its_cpu_init_collection(void)
@@ -1850,7 +1872,7 @@ static void its_cpu_init_collection(void)
        struct its_node *its;
        int cpu;
 
-       spin_lock(&its_lock);
+       raw_spin_lock(&its_lock);
        cpu = smp_processor_id();
 
        list_for_each_entry(its, &its_nodes, entry) {
@@ -1892,7 +1914,7 @@ static void its_cpu_init_collection(void)
                its_send_invall(its, &its->collections[cpu]);
        }
 
-       spin_unlock(&its_lock);
+       raw_spin_unlock(&its_lock);
 }
 
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
@@ -3041,9 +3063,9 @@ static int __init its_probe_one(struct resource *res,
        if (err)
                goto out_free_tables;
 
-       spin_lock(&its_lock);
+       raw_spin_lock(&its_lock);
        list_add(&its->entry, &its_nodes);
-       spin_unlock(&its_lock);
+       raw_spin_unlock(&its_lock);
 
        return 0;
 
@@ -3278,7 +3300,8 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
        }
 
        gic_rdists = rdists;
-       err = its_alloc_lpi_tables();
+
+       err = allocate_lpi_tables();
        if (err)
                return err;
 
diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index 3f9ddb9fafa7..09da5b6b44a1 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -69,7 +69,7 @@ config LEDS_TRIGGER_BACKLIGHT
 
 config LEDS_TRIGGER_CPU
        bool "LED CPU Trigger"
-       depends on LEDS_TRIGGERS
+       depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE
        help
          This allows LEDs to be controlled by active CPUs. This shows
          the active CPUs across an array of LEDs so you can see which
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 4d200883c505..98b64ed5cb81 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -1,6 +1,7 @@
 
 config BCACHE
        tristate "Block device as cache"
+       depends on !PREEMPT_RT_FULL
        ---help---
        Allows a block device to be used as cache for other devices; uses
        a btree for indexing and the layout is optimized for SSDs.
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index eadfcfd106ff..8824aeda85cf 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -671,7 +671,7 @@ static void dm_old_request_fn(struct request_queue *q)
                /* Establish tio->ti before queuing work (map_tio_request) */
                tio->ti = ti;
                kthread_queue_work(&md->kworker, &tio->work);
-               BUG_ON(!irqs_disabled());
+               BUG_ON_NONRT(!irqs_disabled());
        }
 }
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dbf51b4c21b3..5cfccaf87687 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -410,7 +410,7 @@ void raid5_release_stripe(struct stripe_head *sh)
                md_wakeup_thread(conf->mddev->thread);
        return;
 slow_path:
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
        if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
                INIT_LIST_HEAD(&list);
@@ -419,7 +419,7 @@ void raid5_release_stripe(struct stripe_head *sh)
                spin_unlock(&conf->device_lock);
                release_inactive_stripe_list(conf, &list, hash);
        }
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 }
 
 static inline void remove_hash(struct stripe_head *sh)
@@ -2067,8 +2067,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
        struct raid5_percpu *percpu;
        unsigned long cpu;
 
-       cpu = get_cpu();
+       cpu = get_cpu_light();
        percpu = per_cpu_ptr(conf->percpu, cpu);
+       spin_lock(&percpu->lock);
        if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
                ops_run_biofill(sh);
                overlap_clear++;
@@ -2127,7 +2128,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
                        if (test_and_clear_bit(R5_Overlap, &dev->flags))
                                wake_up(&sh->raid_conf->wait_for_overlap);
                }
-       put_cpu();
+       spin_unlock(&percpu->lock);
+       put_cpu_light();
 }
 
 static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
@@ -6781,6 +6783,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
                        __func__, cpu);
                return -ENOMEM;
        }
+       spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
        return 0;
 }
 
@@ -6791,7 +6794,6 @@ static int raid5_alloc_percpu(struct r5conf *conf)
        conf->percpu = alloc_percpu(struct raid5_percpu);
        if (!conf->percpu)
                return -ENOMEM;
-
        err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
        if (!err) {
                conf->scribble_disks = max(conf->raid_disks,
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 2e6123825095..37a6021418a2 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -624,6 +624,7 @@ struct r5conf {
        int                     recovery_disabled;
        /* per cpu variables */
        struct raid5_percpu {
+               spinlock_t      lock;           /* Protection for -RT */
                struct page     *spare_page; /* Used when checking P/Q in raid6 */
                struct flex_array *scribble;   /* space for constructing buffer
                                              * lists and performing address
diff --git a/drivers/mfd/atmel-smc.c b/drivers/mfd/atmel-smc.c
index 7d77948567d7..0adbd2e796fe 100644
--- a/drivers/mfd/atmel-smc.c
+++ b/drivers/mfd/atmel-smc.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/mfd/syscon/atmel-smc.h>
+#include <linux/string.h>
 
 /**
  * atmel_smc_cs_conf_init - initialize a SMC CS conf
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 8136dc7e863d..86e83b9629d7 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -54,6 +54,7 @@ config AD525X_DPOT_SPI
 config ATMEL_TCLIB
        bool "Atmel AT32/AT91 Timer/Counter Library"
        depends on (AVR32 || ARCH_AT91)
+       default y if PREEMPT_RT_FULL
        help
          Select this if you want a library to allocate the Timer/Counter
          blocks found on many Atmel processors.  This facilitates using
@@ -69,8 +70,7 @@ config ATMEL_TCB_CLKSRC
          are combined to make a single 32-bit timer.
 
          When GENERIC_CLOCKEVENTS is defined, the third timer channel
-         may be used as a clock event device supporting oneshot mode
-         (delays of up to two seconds) based on the 32 KiHz clock.
+         may be used as a clock event device supporting oneshot mode.
 
 config ATMEL_TCB_CLKSRC_BLOCK
        int
@@ -84,6 +84,15 @@ config ATMEL_TCB_CLKSRC_BLOCK
          TC can be used for other purposes, such as PWM generation and
          interval timing.
 
+config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
+       bool "TC Block use 32 KiHz clock"
+       depends on ATMEL_TCB_CLKSRC
+       default y if !PREEMPT_RT_FULL
+       help
+         Select this to use 32 KiHz base clock rate as TC block clock
+         source for clock events.
+
+
 config DUMMY_IRQ
        tristate "Dummy IRQ handler"
        default n
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index f1f54a818489..ce102378df02 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1200,15 +1200,12 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
        struct sg_mapping_iter *sg_miter = &host->sg_miter;
        struct variant_data *variant = host->variant;
        void __iomem *base = host->base;
-       unsigned long flags;
        u32 status;
 
        status = readl(base + MMCISTATUS);
 
        dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status);
 
-       local_irq_save(flags);
-
        do {
                unsigned int remain, len;
                char *buffer;
@@ -1248,8 +1245,6 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 
        sg_miter_stop(sg_miter);
 
-       local_irq_restore(flags);
-
        /*
         * If we have less than the fifo 'half-full' threshold to transfer,
         * trigger a PIO interrupt as soon as any data is available.
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 402d9090ad29..9bc02563b853 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -842,9 +842,9 @@ static void poll_vortex(struct net_device *dev)
 {
        struct vortex_private *vp = netdev_priv(dev);
        unsigned long flags;
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 }
 #endif
 
@@ -1908,12 +1908,12 @@ static void vortex_tx_timeout(struct net_device *dev)
                         * Block interrupts because vortex_interrupt does a bare spin_lock()
                         */
                        unsigned long flags;
-                       local_irq_save(flags);
+                       local_irq_save_nort(flags);
                        if (vp->full_bus_master_tx)
                                boomerang_interrupt(dev->irq, dev);
                        else
                                vortex_interrupt(dev->irq, dev);
-                       local_irq_restore(flags);
+                       local_irq_restore_nort(flags);
                }
        }
 
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 00e6f1d155a6..9c69ab2c5b07 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -831,9 +831,8 @@ struct mvpp2_pcpu_stats {
 /* Per-CPU port control */
 struct mvpp2_port_pcpu {
        struct hrtimer tx_done_timer;
+       struct net_device *dev;
        bool timer_scheduled;
-       /* Tasklet for egress finalization */
-       struct tasklet_struct tx_done_tasklet;
 };
 
 struct mvpp2_queue_vector {
@@ -5955,46 +5954,34 @@ static void mvpp2_link_event(struct net_device *dev)
        }
 }
 
-static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu)
-{
-       ktime_t interval;
-
-       if (!port_pcpu->timer_scheduled) {
-               port_pcpu->timer_scheduled = true;
-               interval = MVPP2_TXDONE_HRTIMER_PERIOD_NS;
-               hrtimer_start(&port_pcpu->tx_done_timer, interval,
-                             HRTIMER_MODE_REL_PINNED);
-       }
-}
-
-static void mvpp2_tx_proc_cb(unsigned long data)
+static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
 {
-       struct net_device *dev = (struct net_device *)data;
-       struct mvpp2_port *port = netdev_priv(dev);
-       struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
+       struct net_device *dev;
+       struct mvpp2_port *port;
+       struct mvpp2_port_pcpu *port_pcpu;
        unsigned int tx_todo, cause;
 
+       port_pcpu = container_of(timer, struct mvpp2_port_pcpu, tx_done_timer);
+       dev = port_pcpu->dev;
+
        if (!netif_running(dev))
-               return;
+               return HRTIMER_NORESTART;
+
        port_pcpu->timer_scheduled = false;
+       port = netdev_priv(dev);
 
        /* Process all the Tx queues */
        cause = (1 << port->ntxqs) - 1;
        tx_todo = mvpp2_tx_done(port, cause, smp_processor_id());
 
        /* Set the timer in case not all the packets were processed */
-       if (tx_todo)
-               mvpp2_timer_set(port_pcpu);
-}
-
-static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
-{
-       struct mvpp2_port_pcpu *port_pcpu = container_of(timer,
-                                                        struct mvpp2_port_pcpu,
-                                                        tx_done_timer);
-
-       tasklet_schedule(&port_pcpu->tx_done_tasklet);
+       if (tx_todo && !port_pcpu->timer_scheduled) {
+               port_pcpu->timer_scheduled = true;
+               hrtimer_forward_now(&port_pcpu->tx_done_timer,
+                                   MVPP2_TXDONE_HRTIMER_PERIOD_NS);
 
+               return HRTIMER_RESTART;
+       }
        return HRTIMER_NORESTART;
 }
 
@@ -6484,7 +6471,12 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
            txq_pcpu->count > 0) {
                struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
 
-               mvpp2_timer_set(port_pcpu);
+               if (!port_pcpu->timer_scheduled) {
+                       port_pcpu->timer_scheduled = true;
+                       hrtimer_start(&port_pcpu->tx_done_timer,
+                                     MVPP2_TXDONE_HRTIMER_PERIOD_NS,
+                                     HRTIMER_MODE_REL_PINNED_SOFT);
+               }
        }
 
        return NETDEV_TX_OK;
@@ -6875,7 +6867,6 @@ static int mvpp2_stop(struct net_device *dev)
 
                        hrtimer_cancel(&port_pcpu->tx_done_timer);
                        port_pcpu->timer_scheduled = false;
-                       tasklet_kill(&port_pcpu->tx_done_tasklet);
                }
        }
        mvpp2_cleanup_rxqs(port);
@@ -7648,13 +7639,10 @@ static int mvpp2_port_probe(struct platform_device *pdev,
                        port_pcpu = per_cpu_ptr(port->pcpu, cpu);
 
                        hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
-                                    HRTIMER_MODE_REL_PINNED);
+                                    HRTIMER_MODE_REL_PINNED_SOFT);
                        port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
                        port_pcpu->timer_scheduled = false;
-
-                       tasklet_init(&port_pcpu->tx_done_tasklet,
-                                    mvpp2_tx_proc_cb,
-                                    (unsigned long)dev);
+                       port_pcpu->dev = dev;
                }
        }
 
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index 56f6e3b71f48..a50350d01a80 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
                        while (!ctx->done.done && msecs--)
                                udelay(1000);
                } else {
-                       wait_event_interruptible(ctx->done.wait,
+                       swait_event_interruptible(ctx->done.wait,
                                                 ctx->done.done);
                }
                break;
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index aafa7aa18fbd..388f6d71ba71 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -537,7 +537,7 @@ struct mac80211_hwsim_data {
        unsigned int rx_filter;
        bool started, idle, scanning;
        struct mutex mutex;
-       struct tasklet_hrtimer beacon_timer;
+       struct hrtimer beacon_timer;
        enum ps_mode {
                PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL
        } ps;
@@ -1423,7 +1423,7 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
 {
        struct mac80211_hwsim_data *data = hw->priv;
        data->started = false;
-       tasklet_hrtimer_cancel(&data->beacon_timer);
+       hrtimer_cancel(&data->beacon_timer);
        wiphy_debug(hw->wiphy, "%s\n", __func__);
 }
 
@@ -1546,14 +1546,12 @@ static enum hrtimer_restart
 mac80211_hwsim_beacon(struct hrtimer *timer)
 {
        struct mac80211_hwsim_data *data =
-               container_of(timer, struct mac80211_hwsim_data,
-                            beacon_timer.timer);
+               container_of(timer, struct mac80211_hwsim_data, beacon_timer);
        struct ieee80211_hw *hw = data->hw;
        u64 bcn_int = data->beacon_int;
-       ktime_t next_bcn;
 
        if (!data->started)
-               goto out;
+               return HRTIMER_NORESTART;
 
        ieee80211_iterate_active_interfaces_atomic(
                hw, IEEE80211_IFACE_ITER_NORMAL,
@@ -1565,11 +1563,9 @@ mac80211_hwsim_beacon(struct hrtimer *timer)
                data->bcn_delta = 0;
        }
 
-       next_bcn = ktime_add(hrtimer_get_expires(timer),
-                            ns_to_ktime(bcn_int * 1000));
-       tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS);
-out:
-       return HRTIMER_NORESTART;
+       hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
+                       ns_to_ktime(bcn_int * NSEC_PER_USEC));
+       return HRTIMER_RESTART;
 }
 
 static const char * const hwsim_chanwidths[] = {
@@ -1643,15 +1639,15 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
        mutex_unlock(&data->mutex);
 
        if (!data->started || !data->beacon_int)
-               tasklet_hrtimer_cancel(&data->beacon_timer);
-       else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
+               hrtimer_cancel(&data->beacon_timer);
+       else if (!hrtimer_is_queued(&data->beacon_timer)) {
                u64 tsf = mac80211_hwsim_get_tsf(hw, NULL);
                u32 bcn_int = data->beacon_int;
                u64 until_tbtt = bcn_int - do_div(tsf, bcn_int);
 
-               tasklet_hrtimer_start(&data->beacon_timer,
-                                     ns_to_ktime(until_tbtt * 1000),
-                                     HRTIMER_MODE_REL);
+               hrtimer_start(&data->beacon_timer,
+                             ns_to_ktime(until_tbtt * 1000),
+                             HRTIMER_MODE_REL_SOFT);
        }
 
        return 0;
@@ -1714,7 +1710,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
                            info->enable_beacon, info->beacon_int);
                vp->bcn_en = info->enable_beacon;
                if (data->started &&
-                   !hrtimer_is_queued(&data->beacon_timer.timer) &&
+                   !hrtimer_is_queued(&data->beacon_timer) &&
                    info->enable_beacon) {
                        u64 tsf, until_tbtt;
                        u32 bcn_int;
@@ -1722,9 +1718,9 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
                        tsf = mac80211_hwsim_get_tsf(hw, vif);
                        bcn_int = data->beacon_int;
                        until_tbtt = bcn_int - do_div(tsf, bcn_int);
-                       tasklet_hrtimer_start(&data->beacon_timer,
-                                             ns_to_ktime(until_tbtt * 1000),
-                                             HRTIMER_MODE_REL);
+                       hrtimer_start(&data->beacon_timer,
+                                     ns_to_ktime(until_tbtt * 1000),
+                                     HRTIMER_MODE_REL_SOFT);
                } else if (!info->enable_beacon) {
                        unsigned int count = 0;
                        ieee80211_iterate_active_interfaces_atomic(
@@ -1733,7 +1729,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
                        wiphy_debug(hw->wiphy, "  beaconing vifs remaining: %u",
                                    count);
                        if (count == 0) {
-                               tasklet_hrtimer_cancel(&data->beacon_timer);
+                               hrtimer_cancel(&data->beacon_timer);
                                data->beacon_int = 0;
                        }
                }
@@ -2722,9 +2718,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
                                    data->debugfs,
                                    data, &hwsim_simulate_radar);
 
-       tasklet_hrtimer_init(&data->beacon_timer,
-                            mac80211_hwsim_beacon,
-                            CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+       hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC,
+                    HRTIMER_MODE_ABS_SOFT);
+       data->beacon_timer.function = mac80211_hwsim_beacon;
 
        spin_lock_bh(&hwsim_radio_lock);
        list_add_tail(&data->list, &hwsim_radios);
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 620f5b995a12..7fd1548a2905 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -308,10 +308,11 @@ struct switchtec_user {
 
        enum mrpc_state state;
 
-       struct completion comp;
+       wait_queue_head_t cmd_comp;
        struct kref kref;
        struct list_head list;
 
+       bool cmd_done;
        u32 cmd;
        u32 status;
        u32 return_code;
@@ -333,7 +334,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev)
        stuser->stdev = stdev;
        kref_init(&stuser->kref);
        INIT_LIST_HEAD(&stuser->list);
-       init_completion(&stuser->comp);
+       init_waitqueue_head(&stuser->cmd_comp);
        stuser->event_cnt = atomic_read(&stdev->event_cnt);
 
        dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser);
@@ -416,7 +417,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
        kref_get(&stuser->kref);
        stuser->read_len = sizeof(stuser->data);
        stuser_set_state(stuser, MRPC_QUEUED);
-       init_completion(&stuser->comp);
+       stuser->cmd_done = false;
        list_add_tail(&stuser->list, &stdev->mrpc_queue);
 
        mrpc_cmd_submit(stdev);
@@ -453,7 +454,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev)
                      stuser->read_len);
 
 out:
-       complete_all(&stuser->comp);
+       stuser->cmd_done = true;
+       wake_up_interruptible(&stuser->cmd_comp);
        list_del_init(&stuser->list);
        stuser_put(stuser);
        stdev->mrpc_busy = 0;
@@ -723,10 +725,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data,
        mutex_unlock(&stdev->mrpc_mutex);
 
        if (filp->f_flags & O_NONBLOCK) {
-               if (!try_wait_for_completion(&stuser->comp))
+               if (!READ_ONCE(stuser->cmd_done))
                        return -EAGAIN;
        } else {
-               rc = wait_for_completion_interruptible(&stuser->comp);
+               rc = wait_event_interruptible(stuser->cmd_comp,
+                                             stuser->cmd_done);
                if (rc < 0)
                        return rc;
        }
@@ -774,7 +777,7 @@ static unsigned int switchtec_dev_poll(struct file *filp, poll_table *wait)
        struct switchtec_dev *stdev = stuser->stdev;
        int ret = 0;
 
-       poll_wait(filp, &stuser->comp.wait, wait);
+       poll_wait(filp, &stuser->cmd_comp, wait);
        poll_wait(filp, &stdev->event_wq, wait);
 
        if (lock_mutex_and_test_alive(stdev))
@@ -782,7 +785,7 @@ static unsigned int switchtec_dev_poll(struct file *filp, poll_table *wait)
 
        mutex_unlock(&stdev->mrpc_mutex);
 
-       if (try_wait_for_completion(&stuser->comp))
+       if (READ_ONCE(stuser->cmd_done))
                ret |= POLLIN | POLLRDNORM;
 
        if (stuser->event_cnt != atomic_read(&stdev->event_cnt))
@@ -1259,7 +1262,8 @@ static void stdev_kill(struct switchtec_dev *stdev)
 
        /* Wake up and kill any users waiting on an MRPC request */
        list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) {
-               complete_all(&stuser->comp);
+               stuser->cmd_done = true;
+               wake_up_interruptible(&stuser->cmd_comp);
                list_del_init(&stuser->list);
                stuser_put(stuser);
        }
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 85f9a3eba387..08ea05ddcd82 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1464,11 +1464,11 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev,
 static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen)
 {
        struct fcoe_percpu_s *fps;
-       int rc;
+       int rc, cpu = get_cpu_light();
 
-       fps = &get_cpu_var(fcoe_percpu);
+       fps = &per_cpu(fcoe_percpu, cpu);
        rc = fcoe_get_paged_crc_eof(skb, tlen, fps);
-       put_cpu_var(fcoe_percpu);
+       put_cpu_light();
 
        return rc;
 }
@@ -1655,11 +1655,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
                return 0;
        }
 
-       stats = per_cpu_ptr(lport->stats, get_cpu());
+       stats = per_cpu_ptr(lport->stats, get_cpu_light());
        stats->InvalidCRCCount++;
        if (stats->InvalidCRCCount < 5)
                printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
-       put_cpu();
+       put_cpu_light();
        return -EINVAL;
 }
 
@@ -1702,7 +1702,7 @@ static void fcoe_recv_frame(struct sk_buff *skb)
         */
        hp = (struct fcoe_hdr *) skb_network_header(skb);
 
-       stats = per_cpu_ptr(lport->stats, get_cpu());
+       stats = per_cpu_ptr(lport->stats, get_cpu_light());
        if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
                if (stats->ErrorFrames < 5)
                        printk(KERN_WARNING "fcoe: FCoE version "
@@ -1734,13 +1734,13 @@ static void fcoe_recv_frame(struct sk_buff *skb)
                goto drop;
 
        if (!fcoe_filter_frames(lport, fp)) {
-               put_cpu();
+               put_cpu_light();
                fc_exch_recv(lport, fp);
                return;
        }
 drop:
        stats->ErrorFrames++;
-       put_cpu();
+       put_cpu_light();
        kfree_skb(skb);
 }
 
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 03019e07abb9..9ec11316bfe6 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -835,7 +835,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 
        INIT_LIST_HEAD(&del_list);
 
-       stats = per_cpu_ptr(fip->lp->stats, get_cpu());
+       stats = per_cpu_ptr(fip->lp->stats, get_cpu_light());
 
        list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
                deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
@@ -871,7 +871,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
                                sel_time = fcf->time;
                }
        }
-       put_cpu();
+       put_cpu_light();
 
        list_for_each_entry_safe(fcf, next, &del_list, list) {
                /* Removes fcf from current list */
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 42bcf7f3a0f9..2ce045d6860c 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -833,10 +833,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport,
        }
        memset(ep, 0, sizeof(*ep));
 
-       cpu = get_cpu();
+       cpu = get_cpu_light();
        pool = per_cpu_ptr(mp->pool, cpu);
        spin_lock_bh(&pool->lock);
-       put_cpu();
+       put_cpu_light();
 
        /* peek cache of free slot */
        if (pool->left != FC_XID_UNKNOWN) {
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 70be4425ae0b..a23ef685deac 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -190,7 +190,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
        /* TODO: audit callers to ensure they are ready for qc_issue to
         * unconditionally re-enable interrupts
         */
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        spin_unlock(ap->lock);
 
        /* If the device fell off, no sense in issuing commands */
@@ -252,7 +252,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 
  out:
        spin_lock(ap->lock);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
        return ret;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 3f5a0f0f8b62..c75783143dc1 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -59,12 +59,12 @@ qla2x00_poll(struct rsp_que *rsp)
 {
        unsigned long flags;
        struct qla_hw_data *ha = rsp->hw;
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        if (IS_P3P_TYPE(ha))
                qla82xx_poll(0, rsp);
        else
                ha->isp_ops->intr_handler(0, rsp);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 }
 
 static inline uint8_t *
diff --git a/drivers/staging/greybus/audio_manager.c b/drivers/staging/greybus/audio_manager.c
index aa6508b44fab..045696ce85c7 100644
--- a/drivers/staging/greybus/audio_manager.c
+++ b/drivers/staging/greybus/audio_manager.c
@@ -10,7 +10,7 @@
 #include <linux/sysfs.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/rwlock.h>
+#include <linux/spinlock.h>
 #include <linux/idr.h>
 
 #include "audio_manager.h"
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 9c7bc1ca341a..3d35dad1de2c 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -114,8 +114,6 @@ static bool __target_check_io_state(struct se_cmd *se_cmd,
 {
        struct se_session *sess = se_cmd->se_sess;
 
-       assert_spin_locked(&sess->sess_cmd_lock);
-       WARN_ON_ONCE(!irqs_disabled());
        /*
         * If command already reached CMD_T_COMPLETE state within
         * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 0d0be7d8b9d6..f652e58e2988 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2967,9 +2967,6 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
        __acquires(&cmd->t_state_lock)
 {
 
-       assert_spin_locked(&cmd->t_state_lock);
-       WARN_ON_ONCE(!irqs_disabled());
-
        if (fabric_stop)
                cmd->transport_state |= CMD_T_FABRIC_STOP;
 
@@ -3239,9 +3236,6 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
 {
        int ret;
 
-       assert_spin_locked(&cmd->t_state_lock);
-       WARN_ON_ONCE(!irqs_disabled());
-
        if (!(cmd->transport_state & CMD_T_ABORTED))
                return 0;
        /*
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index d93eee2f101b..0287333b1f3c 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/x86_pkg_temp_thermal.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <linux/thermal.h>
 #include <linux/debugfs.h>
+#include <linux/swork.h>
 #include <asm/cpu_device_id.h>
 #include <asm/mce.h>
 
@@ -329,7 +330,7 @@ static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work)
        schedule_delayed_work_on(cpu, work, ms);
 }
 
-static int pkg_thermal_notify(u64 msr_val)
+static void pkg_thermal_notify_work(struct swork_event *event)
 {
        int cpu = smp_processor_id();
        struct pkg_device *pkgdev;
@@ -348,9 +349,47 @@ static int pkg_thermal_notify(u64 msr_val)
        }
 
        spin_unlock_irqrestore(&pkg_temp_lock, flags);
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static struct swork_event notify_work;
+
+static int pkg_thermal_notify_work_init(void)
+{
+       int err;
+
+       err = swork_get();
+       if (err)
+               return err;
+
+       INIT_SWORK(&notify_work, pkg_thermal_notify_work);
        return 0;
 }
 
+static void pkg_thermal_notify_work_cleanup(void)
+{
+       swork_put();
+}
+
+static int pkg_thermal_notify(u64 msr_val)
+{
+       swork_queue(&notify_work);
+       return 0;
+}
+
+#else  /* !CONFIG_PREEMPT_RT_FULL */
+
+static int pkg_thermal_notify_work_init(void) { return 0; }
+
+static void pkg_thermal_notify_work_cleanup(void) {  }
+
+static int pkg_thermal_notify(u64 msr_val)
+{
+       pkg_thermal_notify_work(NULL);
+       return 0;
+}
+#endif /* CONFIG_PREEMPT_RT_FULL */
+
 static int pkg_temp_thermal_device_add(unsigned int cpu)
 {
        int pkgid = topology_logical_package_id(cpu);
@@ -515,10 +554,15 @@ static int __init pkg_temp_thermal_init(void)
        if (!x86_match_cpu(pkg_temp_thermal_ids))
                return -ENODEV;
 
+       if (!pkg_thermal_notify_work_init())
+               return -ENODEV;
+
        max_packages = topology_max_packages();
        packages = kzalloc(max_packages * sizeof(struct pkg_device *), GFP_KERNEL);
-       if (!packages)
-               return -ENOMEM;
+       if (!packages) {
+               ret = -ENOMEM;
+               goto err;
+       }
 
        ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online",
                                pkg_thermal_cpu_online, pkg_thermal_cpu_offline);
@@ -536,6 +580,7 @@ static int __init pkg_temp_thermal_init(void)
        return 0;
 
 err:
+       pkg_thermal_notify_work_cleanup();
        kfree(packages);
        return ret;
 }
@@ -549,6 +594,7 @@ static void __exit pkg_temp_thermal_exit(void)
        cpuhp_remove_state(pkg_thermal_hp_state);
        debugfs_remove_recursive(debugfs);
        kfree(packages);
+       pkg_thermal_notify_work_cleanup();
 }
 module_exit(pkg_temp_thermal_exit)
 
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index d29b512a7d9f..bc8cbb995b29 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -58,7 +58,16 @@ static struct uart_driver serial8250_reg;
 
 static unsigned int skip_txen_test; /* force skip of txen test at init time */
 
-#define PASS_LIMIT     512
+/*
+ * On -rt we can have a more delays, and legitimately
+ * so - so don't drop work spuriously and spam the
+ * syslog:
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define PASS_LIMIT    1000000
+#else
+# define PASS_LIMIT    512
+#endif
 
 #include <asm/serial.h>
 /*
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index ecf3d631bc09..6e029f34f37f 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -35,6 +35,7 @@
 #include <linux/nmi.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/kdb.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
 #include <linux/ktime.h>
@@ -3224,9 +3225,9 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 
        serial8250_rpm_get(up);
 
-       if (port->sysrq)
+       if (port->sysrq || oops_in_progress)
                locked = 0;
-       else if (oops_in_progress)
+       else if (in_kdb_printk())
                locked = spin_trylock_irqsave(&port->lock, flags);
        else
                spin_lock_irqsave(&port->lock, flags);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index c9f701aca677..81d6b15fb80a 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2236,13 +2236,19 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 
        clk_enable(uap->clk);
 
-       local_irq_save(flags);
+       /*
+        * local_irq_save(flags);
+        *
+        * This local_irq_save() is nonsense. If we come in via sysrq
+        * handling then interrupts are already disabled. Aside of
+        * that the port.sysrq check is racy on SMP regardless.
+       */
        if (uap->port.sysrq)
                locked = 0;
        else if (oops_in_progress)
-               locked = spin_trylock(&uap->port.lock);
+               locked = spin_trylock_irqsave(&uap->port.lock, flags);
        else
-               spin_lock(&uap->port.lock);
+               spin_lock_irqsave(&uap->port.lock, flags);
 
        /*
         *      First save the CR then disable the interrupts
@@ -2268,8 +2274,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
                pl011_write(old_cr, uap, REG_CR);
 
        if (locked)
-               spin_unlock(&uap->port.lock);
-       local_irq_restore(flags);
+               spin_unlock_irqrestore(&uap->port.lock, flags);
 
        clk_disable(uap->clk);
 }
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 26a22b100df1..69117e355bcd 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1311,13 +1311,10 @@ serial_omap_console_write(struct console *co, const char *s,
 
        pm_runtime_get_sync(up->dev);
 
-       local_irq_save(flags);
-       if (up->port.sysrq)
-               locked = 0;
-       else if (oops_in_progress)
-               locked = spin_trylock(&up->port.lock);
+       if (up->port.sysrq || oops_in_progress)
+               locked = spin_trylock_irqsave(&up->port.lock, flags);
        else
-               spin_lock(&up->port.lock);
+               spin_lock_irqsave(&up->port.lock, flags);
 
        /*
         * First save the IER then disable the interrupts
@@ -1346,8 +1343,7 @@ serial_omap_console_write(struct console *co, const char *s,
        pm_runtime_mark_last_busy(up->dev);
        pm_runtime_put_autosuspend(up->dev);
        if (locked)
-               spin_unlock(&up->port.lock);
-       local_irq_restore(flags);
+               spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static int __init
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d0b2e0ed9bab..91f4f2bd55b0 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1775,9 +1775,9 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
         * and no one may trigger the above deadlock situation when
         * running complete() in tasklet.
         */
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        urb->complete(urb);
-       local_irq_restore(flags);
+       local_irq_restore_nort(flags);
 
        usb_anchor_resume_wakeups(anchor);
        atomic_dec(&urb->use_count);
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 17467545391b..42ec6f2db6a9 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1623,7 +1623,7 @@ static void ffs_data_put(struct ffs_data *ffs)
                pr_info("%s(): freeing\n", __func__);
                ffs_data_clear(ffs);
                BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
-                      waitqueue_active(&ffs->ep0req_completion.wait) ||
+                      swait_active(&ffs->ep0req_completion.wait) ||
                       waitqueue_active(&ffs->wait));
                destroy_workqueue(ffs->io_completion_wq);
                kfree(ffs->dev_name);
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 45b334ceaf2e..5f24e6d3b6eb 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -77,9 +77,7 @@ struct f_ncm {
        struct sk_buff                  *skb_tx_ndp;
        u16                             ndp_dgram_count;
        bool                            timer_force_tx;
-       struct tasklet_struct           tx_tasklet;
        struct hrtimer                  task_timer;
-
        bool                            timer_stopping;
 };
 
@@ -1108,7 +1106,7 @@ static struct sk_buff *ncm_wrap_ntb(struct gether *port,
 
                /* Delay the timer. */
                hrtimer_start(&ncm->task_timer, TX_TIMEOUT_NSECS,
-                             HRTIMER_MODE_REL);
+                             HRTIMER_MODE_REL_SOFT);
 
                /* Add the datagram position entries */
                ntb_ndp = skb_put_zero(ncm->skb_tx_ndp, dgram_idx_len);
@@ -1152,17 +1150,15 @@ static struct sk_buff *ncm_wrap_ntb(struct gether *port,
 }
 
 /*
- * This transmits the NTB if there are frames waiting.
+ * The transmit should only be run if no skb data has been sent
+ * for a certain duration.
  */
-static void ncm_tx_tasklet(unsigned long data)
+static enum hrtimer_restart ncm_tx_timeout(struct hrtimer *data)
 {
-       struct f_ncm    *ncm = (void *)data;
-
-       if (ncm->timer_stopping)
-               return;
+       struct f_ncm *ncm = container_of(data, struct f_ncm, task_timer);
 
        /* Only send if data is available. */
-       if (ncm->skb_tx_data) {
+       if (!ncm->timer_stopping && ncm->skb_tx_data) {
                ncm->timer_force_tx = true;
 
                /* XXX This allowance of a NULL skb argument to ndo_start_xmit
@@ -1175,16 +1171,6 @@ static void ncm_tx_tasklet(unsigned long data)
 
                ncm->timer_force_tx = false;
        }
-}
-
-/*
- * The transmit should only be run if no skb data has been sent
- * for a certain duration.
- */
-static enum hrtimer_restart ncm_tx_timeout(struct hrtimer *data)
-{
-       struct f_ncm *ncm = container_of(data, struct f_ncm, task_timer);
-       tasklet_schedule(&ncm->tx_tasklet);
        return HRTIMER_NORESTART;
 }
 
@@ -1517,8 +1503,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
        ncm->port.open = ncm_open;
        ncm->port.close = ncm_close;
 
-       tasklet_init(&ncm->tx_tasklet, ncm_tx_tasklet, (unsigned long) ncm);
-       hrtimer_init(&ncm->task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(&ncm->task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
        ncm->task_timer.function = ncm_tx_timeout;
 
        DBG(cdev, "CDC Network: %s speed IN/%s OUT/%s NOTIFY/%s\n",
@@ -1627,7 +1612,6 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
        DBG(c->cdev, "ncm unbind\n");
 
        hrtimer_cancel(&ncm->task_timer);
-       tasklet_kill(&ncm->tx_tasklet);
 
        ncm_string_defs[0].id = 0;
        usb_free_all_descriptors(f);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 5c28bee327e1..ed49dba4704d 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -347,7 +347,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
        spin_unlock_irq (&epdata->dev->lock);
 
        if (likely (value == 0)) {
-               value = wait_event_interruptible (done.wait, done.done);
+               value = swait_event_interruptible (done.wait, done.done);
                if (value != 0) {
                        spin_lock_irq (&epdata->dev->lock);
                        if (likely (epdata->ep != NULL)) {
@@ -356,7 +356,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
                                usb_ep_dequeue (epdata->ep, epdata->req);
                                spin_unlock_irq (&epdata->dev->lock);
 
-                               wait_event (done.wait, done.done);
+                               swait_event (done.wait, done.done);
                                if (epdata->status == -ECONNRESET)
                                        epdata->status = -EINTR;
                        } else {
diff --git a/fs/aio.c b/fs/aio.c
index 3a749c3a92e3..24c6ceadaae6 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -40,6 +40,7 @@
 #include <linux/ramfs.h>
 #include <linux/percpu-refcount.h>
 #include <linux/mount.h>
+#include <linux/swork.h>
 
 #include <asm/kmap_types.h>
 #include <linux/uaccess.h>
@@ -117,6 +118,7 @@ struct kioctx {
 
        struct rcu_head         free_rcu;
        struct work_struct      free_work;      /* see free_ioctx() */
+       struct swork_event      free_swork;     /* see free_ioctx() */
 
        /*
         * signals when all in-flight requests are done
@@ -259,6 +261,7 @@ static int __init aio_setup(void)
                .mount          = aio_mount,
                .kill_sb        = kill_anon_super,
        };
+       BUG_ON(swork_get());
        aio_mnt = kern_mount(&aio_fs);
        if (IS_ERR(aio_mnt))
                panic("Failed to create aio fs mount.");
@@ -633,9 +636,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
  * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
  * now it's safe to cancel any that need to be.
  */
-static void free_ioctx_users(struct percpu_ref *ref)
+static void free_ioctx_users_work(struct swork_event *sev)
 {
-       struct kioctx *ctx = container_of(ref, struct kioctx, users);
+       struct kioctx *ctx = container_of(sev, struct kioctx, free_swork);
        struct aio_kiocb *req;
 
        spin_lock_irq(&ctx->ctx_lock);
@@ -653,6 +656,14 @@ static void free_ioctx_users(struct percpu_ref *ref)
        percpu_ref_put(&ctx->reqs);
 }
 
+static void free_ioctx_users(struct percpu_ref *ref)
+{
+       struct kioctx *ctx = container_of(ref, struct kioctx, users);
+
+       INIT_SWORK(&ctx->free_swork, free_ioctx_users_work);
+       swork_queue(&ctx->free_swork);
+}
+
 static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 {
        unsigned i, new_nr;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index ce696d6c4641..b120fbd41483 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -20,6 +20,7 @@
 #include <linux/sched.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <linux/uaccess.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 57725d4a8c59..62220508bace 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -148,7 +148,7 @@ static struct dentry *get_next_positive_dentry(struct dentry *prev,
                        parent = p->d_parent;
                        if (!spin_trylock(&parent->d_lock)) {
                                spin_unlock(&p->d_lock);
-                               cpu_relax();
+                               cpu_chill();
                                goto relock;
                        }
                        spin_unlock(&p->d_lock);
diff --git a/fs/buffer.c b/fs/buffer.c
index b96f3b98a6ef..4ca5f222537a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -302,8 +302,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
         * decide that the page is now completely done.
         */
        first = page_buffers(page);
-       local_irq_save(flags);
-       bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+       flags = bh_uptodate_lock_irqsave(first);
        clear_buffer_async_read(bh);
        unlock_buffer(bh);
        tmp = bh;
@@ -316,8 +315,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
                }
                tmp = tmp->b_this_page;
        } while (tmp != bh);
-       bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-       local_irq_restore(flags);
+       bh_uptodate_unlock_irqrestore(first, flags);
 
        /*
         * If none of the buffers had errors and they are all
@@ -329,9 +327,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
        return;
 
 still_busy:
-       bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-       local_irq_restore(flags);
-       return;
+       bh_uptodate_unlock_irqrestore(first, flags);
 }
 
 /*
@@ -358,8 +354,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
        }
 
        first = page_buffers(page);
-       local_irq_save(flags);
-       bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+       flags = bh_uptodate_lock_irqsave(first);
 
        clear_buffer_async_write(bh);
        unlock_buffer(bh);
@@ -371,15 +366,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
                }
                tmp = tmp->b_this_page;
        }
-       bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-       local_irq_restore(flags);
+       bh_uptodate_unlock_irqrestore(first, flags);
        end_page_writeback(page);
        return;
 
 still_busy:
-       bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-       local_irq_restore(flags);
-       return;
+       bh_uptodate_unlock_irqrestore(first, flags);
 }
 EXPORT_SYMBOL(end_buffer_async_write);
 
@@ -3417,6 +3409,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
        struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
        if (ret) {
                INIT_LIST_HEAD(&ret->b_assoc_buffers);
+               buffer_head_init_locks(ret);
                preempt_disable();
                __this_cpu_inc(bh_accounting.nr);
                recalc_bh_state();
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index ef24b4527459..3ce6331a1101 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
        struct inode *inode;
        struct super_block *sb = parent->d_sb;
        struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-       DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+       DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
        cifs_dbg(FYI, "%s: for %s\n", __func__, name->name);
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 28b2e770bb69..b08506ef464a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
@@ -808,6 +809,8 @@ static inline bool fast_dput(struct dentry *dentry)
  */
 void dput(struct dentry *dentry)
 {
+       struct dentry *parent;
+
        if (unlikely(!dentry))
                return;
 
@@ -844,9 +847,18 @@ void dput(struct dentry *dentry)
        return;
 
 kill_it:
-       dentry = dentry_kill(dentry);
-       if (dentry) {
-               cond_resched();
+       parent = dentry_kill(dentry);
+       if (parent) {
+               int r;
+
+               if (parent == dentry) {
+                       /* the task with the highest priority won't schedule */
+                       r = cond_resched();
+                       if (!r)
+                               cpu_chill();
+               } else {
+                       dentry = parent;
+               }
                goto repeat;
        }
 }
@@ -2414,7 +2426,7 @@ void d_delete(struct dentry * dentry)
        if (dentry->d_lockref.count == 1) {
                if (!spin_trylock(&inode->i_lock)) {
                        spin_unlock(&dentry->d_lock);
-                       cpu_relax();
+                       cpu_chill();
                        goto again;
                }
                dentry->d_flags &= ~DCACHE_CANT_MOUNT;
@@ -2459,9 +2471,10 @@ EXPORT_SYMBOL(d_rehash);
 static inline unsigned start_dir_add(struct inode *dir)
 {
 
+       preempt_disable_rt();
        for (;;) {
-               unsigned n = dir->i_dir_seq;
-               if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+               unsigned n = dir->__i_dir_seq;
+               if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n)
                        return n;
                cpu_relax();
        }
@@ -2469,26 +2482,30 @@ static inline unsigned start_dir_add(struct inode *dir)
 
 static inline void end_dir_add(struct inode *dir, unsigned n)
 {
-       smp_store_release(&dir->i_dir_seq, n + 2);
+       smp_store_release(&dir->__i_dir_seq, n + 2);
+       preempt_enable_rt();
 }
 
 static void d_wait_lookup(struct dentry *dentry)
 {
-       if (d_in_lookup(dentry)) {
-               DECLARE_WAITQUEUE(wait, current);
-               add_wait_queue(dentry->d_wait, &wait);
-               do {
-                       set_current_state(TASK_UNINTERRUPTIBLE);
-                       spin_unlock(&dentry->d_lock);
-                       schedule();
-                       spin_lock(&dentry->d_lock);
-               } while (d_in_lookup(dentry));
-       }
+       struct swait_queue __wait;
+
+       if (!d_in_lookup(dentry))
+               return;
+
+       INIT_LIST_HEAD(&__wait.task_list);
+       do {
+               prepare_to_swait(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE);
+               spin_unlock(&dentry->d_lock);
+               schedule();
+               spin_lock(&dentry->d_lock);
+       } while (d_in_lookup(dentry));
+       finish_swait(dentry->d_wait, &__wait);
 }
 
 struct dentry *d_alloc_parallel(struct dentry *parent,
                                const struct qstr *name,
-                               wait_queue_head_t *wq)
+                               struct swait_queue_head *wq)
 {
        unsigned int hash = name->hash;
        struct hlist_bl_head *b = in_lookup_hash(parent, hash);
@@ -2502,7 +2519,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 
 retry:
        rcu_read_lock();
-       seq = smp_load_acquire(&parent->d_inode->i_dir_seq);
+       seq = smp_load_acquire(&parent->d_inode->__i_dir_seq);
        r_seq = read_seqbegin(&rename_lock);
        dentry = __d_lookup_rcu(parent, name, &d_seq);
        if (unlikely(dentry)) {
@@ -2530,7 +2547,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
        }
 
        hlist_bl_lock(b);
-       if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) {
+       if (unlikely(READ_ONCE(parent->d_inode->__i_dir_seq) != seq)) {
                hlist_bl_unlock(b);
                rcu_read_unlock();
                goto retry;
@@ -2603,7 +2620,7 @@ void __d_lookup_done(struct dentry *dentry)
        hlist_bl_lock(b);
        dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
        __hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
-       wake_up_all(dentry->d_wait);
+       swake_up_all(dentry->d_wait);
        dentry->d_wait = NULL;
        hlist_bl_unlock(b);
        INIT_HLIST_NODE(&dentry->d_u.d_alias);
@@ -3638,6 +3655,8 @@ __setup("dhash_entries=", set_dhash_entries);
 
 static void __init dcache_init_early(void)
 {
+       unsigned int loop;
+
        /* If hashes are distributed across NUMA nodes, defer
         * hash allocation until vmalloc space is available.
         */
@@ -3654,10 +3673,14 @@ static void __init dcache_init_early(void)
                                        &d_hash_mask,
                                        0,
                                        0);
+
+       for (loop = 0; loop < (1U << d_hash_shift); loop++)
+               INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
 }
 
 static void __init dcache_init(void)
 {
+       unsigned int loop;
        /*
         * A constructor could be added for stable state like the lists,
         * but it is probably not worth it because of the cache nature
@@ -3680,6 +3703,10 @@ static void __init dcache_init(void)
                                        &d_hash_mask,
                                        0,
                                        0);
+
+       for (loop = 0; loop < (1U << d_hash_shift); loop++)
+               INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
+
 }
 
 /* SLAB cache for __getname() consumers */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 2fabd19cdeea..b768c32631eb 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -587,12 +587,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
  */
 static void ep_poll_safewake(wait_queue_head_t *wq)
 {
-       int this_cpu = get_cpu();
+       int this_cpu = get_cpu_light();
 
        ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
                       ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
 
-       put_cpu();
+       put_cpu_light();
 }
 
 static void ep_remove_wait_queue(struct eppoll_entry *pwq)
diff --git a/fs/exec.c b/fs/exec.c
index 0da4d748b4e6..609aee4dbfa9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1024,12 +1024,14 @@ static int exec_mmap(struct mm_struct *mm)
                }
        }
        task_lock(tsk);
+       preempt_disable_rt();
        active_mm = tsk->active_mm;
        tsk->mm = mm;
        tsk->active_mm = mm;
        activate_mm(active_mm, mm);
        tsk->mm->vmacache_seqnum = 0;
        vmacache_flush(tsk);
+       preempt_enable_rt();
        task_unlock(tsk);
        if (old_mm) {
                up_read(&old_mm->mmap_sem);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index db7590178dfc..d76364124443 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -95,8 +95,7 @@ static void ext4_finish_bio(struct bio *bio)
                 * We check all buffers in the page under BH_Uptodate_Lock
                 * to avoid races with other end io clearing async_write flags
                 */
-               local_irq_save(flags);
-               bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
+               flags = bh_uptodate_lock_irqsave(head);
                do {
                        if (bh_offset(bh) < bio_start ||
                            bh_offset(bh) + bh->b_size > bio_end) {
@@ -108,8 +107,7 @@ static void ext4_finish_bio(struct bio *bio)
                        if (bio->bi_status)
                                buffer_io_error(bh);
                } while ((bh = bh->b_this_page) != head);
-               bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-               local_irq_restore(flags);
+               bh_uptodate_unlock_irqrestore(head, flags);
                if (!under_io) {
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
                        if (data_page)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 29868c35c19a..76d354eee035 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1188,7 +1188,7 @@ static int fuse_direntplus_link(struct file *file,
        struct inode *dir = d_inode(parent);
        struct fuse_conn *fc;
        struct inode *inode;
-       DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+       DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
        if (!o->nodeid) {
                /*
diff --git a/fs/inode.c b/fs/inode.c
index cfc36d11bcb3..b77ce179798a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -154,7 +154,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
        inode->i_bdev = NULL;
        inode->i_cdev = NULL;
        inode->i_link = NULL;
-       inode->i_dir_seq = 0;
+       inode->__i_dir_seq = 0;
        inode->i_rdev = 0;
        inode->dirtied_when = 0;
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 3aabe553fc45..b5d63bf1ad8e 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -90,7 +90,7 @@ static struct dentry *next_positive(struct dentry *parent,
                                    struct list_head *from,
                                    int count)
 {
-       unsigned *seq = &parent->d_inode->i_dir_seq, n;
+       unsigned *seq = &parent->d_inode->__i_dir_seq, n;
        struct dentry *res;
        struct list_head *p;
        bool skipped;
@@ -123,8 +123,9 @@ static struct dentry *next_positive(struct dentry *parent,
 static void move_cursor(struct dentry *cursor, struct list_head *after)
 {
        struct dentry *parent = cursor->d_parent;
-       unsigned n, *seq = &parent->d_inode->i_dir_seq;
+       unsigned n, *seq = &parent->d_inode->__i_dir_seq;
        spin_lock(&parent->d_lock);
+       preempt_disable_rt();
        for (;;) {
                n = *seq;
                if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
@@ -137,6 +138,7 @@ static void move_cursor(struct dentry *cursor, struct list_head *after)
        else
                list_add_tail(&cursor->d_child, &parent->d_subdirs);
        smp_store_release(seq, n + 2);
+       preempt_enable_rt();
        spin_unlock(&parent->d_lock);
 }
 
diff --git a/fs/locks.c b/fs/locks.c
index 665e3ce9ab47..47b66bfc4fa3 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -945,7 +945,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
                        return -ENOMEM;
        }
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
        if (request->fl_flags & FL_ACCESS)
                goto find_conflict;
@@ -986,7 +986,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 
 out:
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
        if (new_fl)
                locks_free_lock(new_fl);
        locks_dispose_list(&dispose);
@@ -1023,7 +1023,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
                new_fl2 = locks_alloc_lock();
        }
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
        /*
         * New lock request. Walk all POSIX locks and look for conflicts. If
@@ -1195,7 +1195,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
        }
  out:
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
        /*
         * Free any unused locks.
         */
@@ -1470,7 +1470,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
                return error;
        }
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
 
        time_out_leases(inode, &dispose);
@@ -1522,13 +1522,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
        locks_insert_block(fl, new_fl);
        trace_break_lease_block(inode, new_fl);
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
 
        locks_dispose_list(&dispose);
        error = wait_event_interruptible_timeout(new_fl->fl_wait,
                                                !new_fl->fl_next, break_time);
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
        trace_break_lease_unblock(inode, new_fl);
        locks_delete_block(new_fl);
@@ -1545,7 +1545,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
        }
 out:
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
        locks_dispose_list(&dispose);
        locks_free_lock(new_fl);
        return error;
@@ -1619,7 +1619,7 @@ int fcntl_getlease(struct file *filp)
 
        ctx = smp_load_acquire(&inode->i_flctx);
        if (ctx && !list_empty_careful(&ctx->flc_lease)) {
-               percpu_down_read_preempt_disable(&file_rwsem);
+               percpu_down_read(&file_rwsem);
                spin_lock(&ctx->flc_lock);
                time_out_leases(inode, &dispose);
                list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
@@ -1629,7 +1629,7 @@ int fcntl_getlease(struct file *filp)
                        break;
                }
                spin_unlock(&ctx->flc_lock);
-               percpu_up_read_preempt_enable(&file_rwsem);
+               percpu_up_read(&file_rwsem);
 
                locks_dispose_list(&dispose);
        }
@@ -1704,7 +1704,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
                return -EINVAL;
        }
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
        time_out_leases(inode, &dispose);
        error = check_conflicting_open(dentry, arg, lease->fl_flags);
@@ -1775,7 +1775,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
                lease->fl_lmops->lm_setup(lease, priv);
 out:
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
        locks_dispose_list(&dispose);
        if (is_deleg)
                inode_unlock(inode);
@@ -1798,7 +1798,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
                return error;
        }
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
        list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
                if (fl->fl_file == filp &&
@@ -1811,7 +1811,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
        if (victim)
                error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
        locks_dispose_list(&dispose);
        return error;
 }
@@ -2542,13 +2542,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
        if (list_empty(&ctx->flc_lease))
                return;
 
-       percpu_down_read_preempt_disable(&file_rwsem);
+       percpu_down_read(&file_rwsem);
        spin_lock(&ctx->flc_lock);
        list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
                if (filp == fl->fl_file)
                        lease_modify(fl, F_UNLCK, &dispose);
        spin_unlock(&ctx->flc_lock);
-       percpu_up_read_preempt_enable(&file_rwsem);
+       percpu_up_read(&file_rwsem);
 
        locks_dispose_list(&dispose);
 }
diff --git a/fs/namei.c b/fs/namei.c
index 0b46b858cd42..f5c6c2ec44ce 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1627,7 +1627,7 @@ static struct dentry *lookup_slow(const struct qstr *name,
 {
        struct dentry *dentry = ERR_PTR(-ENOENT), *old;
        struct inode *inode = dir->d_inode;
-       DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+       DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
        inode_lock_shared(inode);
        /* Don't go there if it's already dead */
@@ -3100,7 +3100,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
        struct dentry *dentry;
        int error, create_error = 0;
        umode_t mode = op->mode;
-       DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+       DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
        if (unlikely(IS_DEADDIR(dir_inode)))
                return -ENOENT;
diff --git a/fs/namespace.c b/fs/namespace.c
index 9dc146e7b5e0..85bfe5e55adf 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -14,6 +14,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <linux/security.h>
 #include <linux/cred.h>
 #include <linux/idr.h>
@@ -353,8 +354,11 @@ int __mnt_want_write(struct vfsmount *m)
         * incremented count after it has set MNT_WRITE_HOLD.
         */
        smp_mb();
-       while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
-               cpu_relax();
+       while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
+               preempt_enable();
+               cpu_chill();
+               preempt_disable();
+       }
        /*
         * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
         * be set to match its requirements. So we must not load that until
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 606dd3871f66..fa41eb75b4d8 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -150,11 +150,11 @@ static int nfs_delegation_claim_opens(struct inode *inode,
                sp = state->owner;
                /* Block nfs4_proc_unlck */
                mutex_lock(&sp->so_delegreturn_mutex);
-               seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+               seq = read_seqbegin(&sp->so_reclaim_seqlock);
                err = nfs4_open_delegation_recall(ctx, state, stateid, type);
                if (!err)
                        err = nfs_delegation_claim_locks(ctx, state, stateid);
-               if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+               if (!err && read_seqretry(&sp->so_reclaim_seqlock, seq))
                        err = -EAGAIN;
                mutex_unlock(&sp->so_delegreturn_mutex);
                put_nfs_open_context(ctx);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index bf2c43635062..f43f5da4a8c3 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -452,7 +452,7 @@ static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
        struct qstr filename = QSTR_INIT(entry->name, entry->len);
-       DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+       DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
        struct dentry *dentry;
        struct dentry *alias;
        struct inode *dir = d_inode(parent);
@@ -1443,7 +1443,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
                    struct file *file, unsigned open_flags,
                    umode_t mode, int *opened)
 {
-       DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+       DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
        struct nfs_open_context *ctx;
        struct dentry *res;
        struct iattr attr = { .ia_valid = ATTR_OPEN };
@@ -1763,7 +1763,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 
        trace_nfs_rmdir_enter(dir, dentry);
        if (d_really_is_positive(dentry)) {
+#ifdef CONFIG_PREEMPT_RT_BASE
+               down(&NFS_I(d_inode(dentry))->rmdir_sem);
+#else
                down_write(&NFS_I(d_inode(dentry))->rmdir_sem);
+#endif
                error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
                /* Ensure the VFS deletes this inode */
                switch (error) {
@@ -1773,7 +1777,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
                case -ENOENT:
                        nfs_dentry_handle_enoent(dentry);
                }
+#ifdef CONFIG_PREEMPT_RT_BASE
+               up(&NFS_I(d_inode(dentry))->rmdir_sem);
+#else
                up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
+#endif
        } else
                error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
        trace_nfs_rmdir_exit(dir, dentry, error);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 134d9f560240..ff64167f9811 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2014,7 +2014,11 @@ static void init_once(void *foo)
        atomic_long_set(&nfsi->nrequests, 0);
        atomic_long_set(&nfsi->commit_info.ncommit, 0);
        atomic_set(&nfsi->commit_info.rpcs_out, 0);
+#ifdef CONFIG_PREEMPT_RT_BASE
+       sema_init(&nfsi->rmdir_sem, 1);
+#else
        init_rwsem(&nfsi->rmdir_sem);
+#endif
        mutex_init(&nfsi->commit_mutex);
        nfs4_init_once(nfsi);
 }
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index a73144b3cb8c..0c403d280b96 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -112,7 +112,7 @@ struct nfs4_state_owner {
        unsigned long        so_flags;
        struct list_head     so_states;
        struct nfs_seqid_counter so_seqid;
-       seqcount_t           so_reclaim_seqcount;
+       seqlock_t            so_reclaim_seqlock;
        struct mutex         so_delegreturn_mutex;
 };
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a3b67d3b1dfb..4ce6ec109c2b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2700,7 +2700,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
        unsigned int seq;
        int ret;
 
-       seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+       seq = raw_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
 
        ret = _nfs4_proc_open(opendata);
        if (ret != 0)
@@ -2738,7 +2738,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 
        if (d_inode(dentry) == state->inode) {
                nfs_inode_attach_open_context(ctx);
-               if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+               if (read_seqretry(&sp->so_reclaim_seqlock, seq))
                        nfs4_schedule_stateid_recovery(server, state);
        }
 out:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e1d88bca815e..c51bcc176026 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -494,7 +494,7 @@ nfs4_alloc_state_owner(struct nfs_server *server,
        nfs4_init_seqid_counter(&sp->so_seqid);
        atomic_set(&sp->so_count, 1);
        INIT_LIST_HEAD(&sp->so_lru);
-       seqcount_init(&sp->so_reclaim_seqcount);
+       seqlock_init(&sp->so_reclaim_seqlock);
        mutex_init(&sp->so_delegreturn_mutex);
        return sp;
 }
@@ -1521,8 +1521,12 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
         * recovering after a network partition or a reboot from a
         * server that doesn't support a grace period.
         */
+#ifdef CONFIG_PREEMPT_RT_FULL
+       write_seqlock(&sp->so_reclaim_seqlock);
+#else
+       write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
+#endif
        spin_lock(&sp->so_lock);
-       raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
        list_for_each_entry(state, &sp->so_states, open_states) {
                if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1591,14 +1595,20 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
                spin_lock(&sp->so_lock);
                goto restart;
        }
-       raw_write_seqcount_end(&sp->so_reclaim_seqcount);
        spin_unlock(&sp->so_lock);
+#ifdef CONFIG_PREEMPT_RT_FULL
+       write_sequnlock(&sp->so_reclaim_seqlock);
+#else
+       write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
+#endif
        return 0;
 out_err:
        nfs4_put_open_state(state);
-       spin_lock(&sp->so_lock);
-       raw_write_seqcount_end(&sp->so_reclaim_seqcount);
-       spin_unlock(&sp->so_lock);
+#ifdef CONFIG_PREEMPT_RT_FULL
+       write_sequnlock(&sp->so_reclaim_seqlock);
+#else
+       write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
+#endif
        return status;
 }
 
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 630b4a3c1a93..0dc1d3e6a62f 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -13,7 +13,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/swait.h>
 #include <linux/namei.h>
 #include <linux/fsnotify.h>
 
@@ -52,6 +52,29 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
                rpc_restart_call_prepare(task);
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void nfs_down_anon(struct semaphore *sema)
+{
+       down(sema);
+}
+
+static void nfs_up_anon(struct semaphore *sema)
+{
+       up(sema);
+}
+
+#else
+static void nfs_down_anon(struct rw_semaphore *rwsem)
+{
+       down_read_non_owner(rwsem);
+}
+
+static void nfs_up_anon(struct rw_semaphore *rwsem)
+{
+       up_read_non_owner(rwsem);
+}
+#endif
+
 /**
  * nfs_async_unlink_release - Release the sillydelete data.
  * @task: rpc_task of the sillydelete
@@ -65,7 +88,7 @@ static void nfs_async_unlink_release(void *calldata)
        struct dentry *dentry = data->dentry;
        struct super_block *sb = dentry->d_sb;
 
-       up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
+       nfs_up_anon(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
        d_lookup_done(dentry);
        nfs_free_unlinkdata(data);
        dput(dentry);
@@ -118,10 +141,10 @@ static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
        struct inode *dir = d_inode(dentry->d_parent);
        struct dentry *alias;
 
-       down_read_non_owner(&NFS_I(dir)->rmdir_sem);
+       nfs_down_anon(&NFS_I(dir)->rmdir_sem);
        alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq);
        if (IS_ERR(alias)) {
-               up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+               nfs_up_anon(&NFS_I(dir)->rmdir_sem);
                return 0;
        }
        if (!d_in_lookup(alias)) {
@@ -143,7 +166,7 @@ static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
                        ret = 0;
                spin_unlock(&alias->d_lock);
                dput(alias);
-               up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+               nfs_up_anon(&NFS_I(dir)->rmdir_sem);
                /*
                 * If we'd displaced old cached devname, free it.  At that
                 * point dentry is definitely not a root, so we won't need
@@ -183,7 +206,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name)
                goto out_free_name;
        }
        data->res.dir_attr = &data->dir_attr;
-       init_waitqueue_head(&data->wq);
+       init_swait_queue_head(&data->wq);
 
        status = -EBUSY;
        spin_lock(&dentry->d_lock);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index cc91856b5e2d..a982d7c3ad91 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -93,13 +93,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
                        ofs = 0;
                        if (file_ofs < init_size)
                                ofs = init_size - file_ofs;
-                       local_irq_save(flags);
+                       local_irq_save_nort(flags);
                        kaddr = kmap_atomic(page);
                        memset(kaddr + bh_offset(bh) + ofs, 0,
                                        bh->b_size - ofs);
                        flush_dcache_page(page);
                        kunmap_atomic(kaddr);
-                       local_irq_restore(flags);
+                       local_irq_restore_nort(flags);
                }
        } else {
                clear_buffer_uptodate(bh);
@@ -108,8 +108,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
                                "0x%llx.", (unsigned long long)bh->b_blocknr);
        }
        first = page_buffers(page);
-       local_irq_save(flags);
-       bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+       flags = bh_uptodate_lock_irqsave(first);
        clear_buffer_async_read(bh);
        unlock_buffer(bh);
        tmp = bh;
@@ -124,8 +123,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
                }
                tmp = tmp->b_this_page;
        } while (tmp != bh);
-       bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-       local_irq_restore(flags);
+       bh_uptodate_unlock_irqrestore(first, flags);
        /*
         * If none of the buffers had errors then we can set the page uptodate,
         * but we first have to perform the post read mst fixups, if the
@@ -146,13 +144,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
                recs = PAGE_SIZE / rec_size;
                /* Should have been verified before we got here... */
                BUG_ON(!recs);
-               local_irq_save(flags);
+               local_irq_save_nort(flags);
                kaddr = kmap_atomic(page);
                for (i = 0; i < recs; i++)
                        post_read_mst_fixup((NTFS_RECORD*)(kaddr +
                                        i * rec_size), rec_size);
                kunmap_atomic(kaddr);
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
                flush_dcache_page(page);
                if (likely(page_uptodate && !PageError(page)))
                        SetPageUptodate(page);
@@ -160,9 +158,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
        unlock_page(page);
        return;
 still_busy:
-       bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-       local_irq_restore(flags);
-       return;
+       bh_uptodate_unlock_irqrestore(first, flags);
 }
 
 /**
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 4ac811e1a26c..9dcb40690cde 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -386,9 +386,9 @@ static inline void task_context_switch_counts(struct seq_file *m,
 static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 {
        seq_printf(m, "Cpus_allowed:\t%*pb\n",
-                  cpumask_pr_args(&task->cpus_allowed));
+                  cpumask_pr_args(task->cpus_ptr));
        seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
-                  cpumask_pr_args(&task->cpus_allowed));
+                  cpumask_pr_args(task->cpus_ptr));
 }
 
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9063738ff1f0..4085e56e261c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1900,7 +1900,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 
        child = d_hash_and_lookup(dir, &qname);
        if (!child) {
-               DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+               DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
                child = d_alloc_parallel(dir, &qname, &wq);
                if (IS_ERR(child))
                        goto end_instantiate;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 82ac5f682b73..c35714621a38 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -679,7 +679,7 @@ static bool proc_sys_fill_cache(struct file *file,
 
        child = d_lookup(dir, &qname);
        if (!child) {
-               DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+               DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
                child = d_alloc_parallel(dir, &qname, &wq);
                if (IS_ERR(child))
                        return false;
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index 23a9c28ad8ea..6a73c4fa88e7 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/buffer_head.h>
+#include <linux/locallock.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -25,6 +26,8 @@ struct squashfs_stream {
        void            *stream;
 };
 
+static DEFINE_LOCAL_IRQ_LOCK(stream_lock);
+
 void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
                                                void *comp_opts)
 {
@@ -79,10 +82,15 @@ int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
 {
        struct squashfs_stream __percpu *percpu =
                        (struct squashfs_stream __percpu *) msblk->stream;
-       struct squashfs_stream *stream = get_cpu_ptr(percpu);
-       int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
-               offset, length, output);
-       put_cpu_ptr(stream);
+       struct squashfs_stream *stream;
+       int res;
+
+       stream = get_locked_ptr(stream_lock, percpu);
+
+       res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+                       offset, length, output);
+
+       put_locked_ptr(stream_lock, stream);
 
        if (res < 0)
                ERROR("%s decompression failed, data probably corrupt\n",
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 040612ec9598..b3d9d435926c 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, int flags,
                                break;
                }
                spin_unlock_irq(&ctx->wqh.lock);
-               cpu_relax();
+               if (isalarm(ctx))
+                       hrtimer_wait_for_timer(&ctx->t.alarm.timer);
+               else
+                       hrtimer_wait_for_timer(&ctx->t.tmr);
        }
 
        /*
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b0cccf8a81a8..eaa4383defec 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -120,8 +120,7 @@ xfs_finish_page_writeback(
        ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
        ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
 
-       local_irq_save(flags);
-       bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
+       flags = bh_uptodate_lock_irqsave(head);
        do {
                if (off >= bvec->bv_offset &&
                    off < bvec->bv_offset + bvec->bv_len) {
@@ -143,8 +142,7 @@ xfs_finish_page_writeback(
                }
                off += bh->b_size;
        } while ((bh = bh->b_this_page) != head);
-       bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-       local_irq_restore(flags);
+       bh_uptodate_unlock_irqrestore(head, flags);
 
        if (!busy)
                end_page_writeback(bvec->bv_page);
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 1b473efd9eb6..89ee5e1dac48 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -134,6 +134,7 @@
 
 #define acpi_cache_t                        struct kmem_cache
 #define acpi_spinlock                       spinlock_t *
+#define acpi_raw_spinlock              raw_spinlock_t *
 #define acpi_cpu_flags                      unsigned long
 
 /* Use native linux version of acpi_os_allocate_zeroed */
@@ -152,6 +153,20 @@
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
 
+#define acpi_os_create_raw_lock(__handle)                      \
+({                                                             \
+        raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock));   \
+                                                               \
+        if (lock) {                                            \
+               *(__handle) = lock;                             \
+               raw_spin_lock_init(*(__handle));                \
+        }                                                      \
+        lock ? AE_OK : AE_NO_MEMORY;                           \
+ })
+
+#define acpi_os_delete_raw_lock(__handle)      kfree(__handle)
+
+
 /*
  * OSL interfaces used by debugger/disassembler
  */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index ae1a33aa8955..c6d04eca8345 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -234,6 +234,20 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 # define WARN_ON_SMP(x)                        ({0;})
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define BUG_ON_RT(c)                  BUG_ON(c)
+# define BUG_ON_NONRT(c)               do { } while (0)
+# define WARN_ON_RT(condition)         WARN_ON(condition)
+# define WARN_ON_NONRT(condition)      do { } while (0)
+# define WARN_ON_ONCE_NONRT(condition) do { } while (0)
+#else
+# define BUG_ON_RT(c)                  do { } while (0)
+# define BUG_ON_NONRT(c)               BUG_ON(c)
+# define WARN_ON_RT(condition)         do { } while (0)
+# define WARN_ON_NONRT(condition)      WARN_ON(condition)
+# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition)
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 994cbb0f7ffc..0d4b7e3489a9 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -226,7 +226,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
        return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
 }
 
-
+void __blk_mq_complete_request_remote_work(struct work_struct *work);
 int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, blk_status_t error);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4d4af0e94059..cbf9d5730dd3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,6 +27,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/swork.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -134,6 +135,9 @@ typedef __u32 __bitwise req_flags_t;
  */
 struct request {
        struct list_head queuelist;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct work_struct work;
+#endif
        union {
                struct __call_single_data csd;
                u64 fifo_time;
@@ -596,6 +600,7 @@ struct request_queue {
 #endif
        struct rcu_head         rcu_head;
        wait_queue_head_t       mq_freeze_wq;
+       struct swork_event      mq_pcpu_wake;
        struct percpu_ref       q_usage_counter;
        struct list_head        all_q_node;
 
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index a19519f4241d..40dd5ef9c154 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -4,6 +4,39 @@
 
 #include <linux/preempt.h>
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+extern void __local_bh_disable(void);
+extern void _local_bh_enable(void);
+extern void __local_bh_enable(void);
+
+static inline void local_bh_disable(void)
+{
+       __local_bh_disable();
+}
+
+static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+       __local_bh_disable();
+}
+
+static inline void local_bh_enable(void)
+{
+       __local_bh_enable();
+}
+
+static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+       __local_bh_enable();
+}
+
+static inline void local_bh_enable_ip(unsigned long ip)
+{
+       __local_bh_enable();
+}
+
+#else
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
 #else
@@ -31,5 +64,6 @@ static inline void local_bh_enable(void)
 {
        __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
 }
+#endif
 
 #endif /* _LINUX_BH_H */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index afa37f807f12..48505fade7e1 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -76,8 +76,50 @@ struct buffer_head {
        struct address_space *b_assoc_map;      /* mapping this buffer is
                                                   associated with */
        atomic_t b_count;               /* users using this buffer_head */
+#ifdef CONFIG_PREEMPT_RT_BASE
+       spinlock_t b_uptodate_lock;
+#if IS_ENABLED(CONFIG_JBD2)
+       spinlock_t b_state_lock;
+       spinlock_t b_journal_head_lock;
+#endif
+#endif
 };
 
+static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh)
+{
+       unsigned long flags;
+
+#ifndef CONFIG_PREEMPT_RT_BASE
+       local_irq_save(flags);
+       bit_spin_lock(BH_Uptodate_Lock, &bh->b_state);
+#else
+       spin_lock_irqsave(&bh->b_uptodate_lock, flags);
+#endif
+       return flags;
+}
+
+static inline void
+bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags)
+{
+#ifndef CONFIG_PREEMPT_RT_BASE
+       bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state);
+       local_irq_restore(flags);
+#else
+       spin_unlock_irqrestore(&bh->b_uptodate_lock, flags);
+#endif
+}
+
+static inline void buffer_head_init_locks(struct buffer_head *bh)
+{
+#ifdef CONFIG_PREEMPT_RT_BASE
+       spin_lock_init(&bh->b_uptodate_lock);
+#if IS_ENABLED(CONFIG_JBD2)
+       spin_lock_init(&bh->b_state_lock);
+       spin_lock_init(&bh->b_journal_head_lock);
+#endif
+#endif
+}
+
 /*
  * macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
  * and buffer_foo() functions.
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index e7905d9353e8..4ecf7875e04f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -19,6 +19,7 @@
 #include <linux/percpu-rwsem.h>
 #include <linux/workqueue.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/swork.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -152,6 +153,7 @@ struct cgroup_subsys_state {
        /* percpu_ref killing and RCU release */
        struct rcu_head rcu_head;
        struct work_struct destroy_work;
+       struct swork_event destroy_swork;
 
        /*
         * PI: the parent css.  Placed here for cache proximity to following
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 7828451e161a..f5838b10cf84 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,7 +9,7 @@
  * See kernel/sched/completion.c for details.
  */
 
-#include <linux/wait.h>
+#include <linux/swait.h>
 #ifdef CONFIG_LOCKDEP_COMPLETIONS
 #include <linux/lockdep.h>
 #endif
@@ -28,7 +28,7 @@
  */
 struct completion {
        unsigned int done;
-       wait_queue_head_t wait;
+       struct swait_queue_head wait;
 #ifdef CONFIG_LOCKDEP_COMPLETIONS
        struct lockdep_map_cross map;
 #endif
@@ -67,11 +67,11 @@ static inline void complete_release_commit(struct completion *x) {}
 
 #ifdef CONFIG_LOCKDEP_COMPLETIONS
 #define COMPLETION_INITIALIZER(work) \
-       { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
+       { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
        STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) }
 #else
 #define COMPLETION_INITIALIZER(work) \
-       { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+       { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
 #endif
 
 #define COMPLETION_INITIALIZER_ONSTACK(work) \
@@ -117,7 +117,7 @@ static inline void complete_release_commit(struct completion *x) {}
 static inline void __init_completion(struct completion *x)
 {
        x->done = 0;
-       init_waitqueue_head(&x->wait);
+       init_swait_queue_head(&x->wait);
 }
 
 /**
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 2a378d261914..b418d3c5159d 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -120,6 +120,8 @@ extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
+extern void pin_current_cpu(void);
+extern void unpin_current_cpu(void);
 
 #else /* CONFIG_HOTPLUG_CPU */
 
@@ -130,6 +132,9 @@ static inline void cpus_read_unlock(void) { }
 static inline void lockdep_assert_cpus_held(void) { }
 static inline void cpu_hotplug_disable(void) { }
 static inline void cpu_hotplug_enable(void) { }
+static inline void pin_current_cpu(void) { }
+static inline void unpin_current_cpu(void) { }
+
 #endif /* !CONFIG_HOTPLUG_CPU */
 
 /* Wrappers which go away once all code is converted */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 006f4ccda5f5..d413993f7f17 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -107,7 +107,7 @@ struct dentry {
 
        union {
                struct list_head d_lru;         /* LRU list */
-               wait_queue_head_t *d_wait;      /* in-lookup ones only */
+               struct swait_queue_head *d_wait;        /* in-lookup ones only */
        };
        struct list_head d_child;       /* child of parent list */
        struct list_head d_subdirs;     /* our children */
@@ -238,7 +238,7 @@ extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
 extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *);
 extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
-                                       wait_queue_head_t *);
+                                       struct swait_queue_head *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern struct dentry * d_exact_alias(struct dentry *, struct inode *);
diff --git a/include/linux/delay.h b/include/linux/delay.h
index b78bab4395d8..7c4bc414a504 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -64,4 +64,10 @@ static inline void ssleep(unsigned int seconds)
        msleep(seconds * 1000);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void cpu_chill(void);
+#else
+# define cpu_chill()   cpu_relax()
+#endif
+
 #endif /* defined(_LINUX_DELAY_H) */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cc613f20e5a6..b806e2116f5c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -655,7 +655,7 @@ struct inode {
                struct block_device     *i_bdev;
                struct cdev             *i_cdev;
                char                    *i_link;
-               unsigned                i_dir_seq;
+               unsigned                __i_dir_seq;
        };
 
        __u32                   i_generation;
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 776f90f3a1cd..5f0bd7a3e6a7 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 
@@ -66,7 +67,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
-       preempt_disable();
+       preempt_disable_nort();
        pagefault_disable();
        return page_address(page);
 }
@@ -75,7 +76,7 @@ static inline void *kmap_atomic(struct page *page)
 static inline void __kunmap_atomic(void *addr)
 {
        pagefault_enable();
-       preempt_enable();
+       preempt_enable_nort();
 }
 
 #define kmap_atomic_pfn(pfn)   kmap_atomic(pfn_to_page(pfn))
@@ -87,32 +88,51 @@ static inline void __kunmap_atomic(void *addr)
 
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 DECLARE_PER_CPU(int, __kmap_atomic_idx);
+#endif
 
 static inline int kmap_atomic_idx_push(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
        int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
 
-#ifdef CONFIG_DEBUG_HIGHMEM
+# ifdef CONFIG_DEBUG_HIGHMEM
        WARN_ON_ONCE(in_irq() && !irqs_disabled());
        BUG_ON(idx >= KM_TYPE_NR);
-#endif
+# endif
        return idx;
+#else
+       current->kmap_idx++;
+       BUG_ON(current->kmap_idx > KM_TYPE_NR);
+       return current->kmap_idx - 1;
+#endif
 }
 
 static inline int kmap_atomic_idx(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
        return __this_cpu_read(__kmap_atomic_idx) - 1;
+#else
+       return current->kmap_idx - 1;
+#endif
 }
 
 static inline void kmap_atomic_idx_pop(void)
 {
-#ifdef CONFIG_DEBUG_HIGHMEM
+#ifndef CONFIG_PREEMPT_RT_FULL
+# ifdef CONFIG_DEBUG_HIGHMEM
        int idx = __this_cpu_dec_return(__kmap_atomic_idx);
 
        BUG_ON(idx < 0);
-#else
+# else
        __this_cpu_dec(__kmap_atomic_idx);
+# endif
+#else
+       current->kmap_idx--;
+# ifdef CONFIG_DEBUG_HIGHMEM
+       BUG_ON(current->kmap_idx < 0);
+# endif
 #endif
 }
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 012c37fdb688..3bd606859b0a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -22,19 +22,42 @@
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
+#include <linux/wait.h>
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
 
 /*
  * Mode arguments of xxx_hrtimer functions:
+ *
+ * HRTIMER_MODE_ABS            - Time value is absolute
+ * HRTIMER_MODE_REL            - Time value is relative to now
+ * HRTIMER_MODE_PINNED         - Timer is bound to CPU (is only considered
+ *                               when starting the timer)
+ * HRTIMER_MODE_SOFT           - Timer callback function will be executed in
+ *                               soft irq context
  */
 enum hrtimer_mode {
-       HRTIMER_MODE_ABS = 0x0,         /* Time value is absolute */
-       HRTIMER_MODE_REL = 0x1,         /* Time value is relative to now */
-       HRTIMER_MODE_PINNED = 0x02,     /* Timer is bound to CPU */
-       HRTIMER_MODE_ABS_PINNED = 0x02,
-       HRTIMER_MODE_REL_PINNED = 0x03,
+       HRTIMER_MODE_ABS        = 0x00,
+       HRTIMER_MODE_REL        = 0x01,
+       HRTIMER_MODE_PINNED     = 0x02,
+       HRTIMER_MODE_SOFT       = 0x04,
+       HRTIMER_MODE_HARD       = 0x08,
+
+       HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
+       HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
+
+       HRTIMER_MODE_ABS_SOFT   = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT,
+       HRTIMER_MODE_REL_SOFT   = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT,
+
+       HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
+       HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
+
+       HRTIMER_MODE_ABS_HARD   = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD,
+       HRTIMER_MODE_REL_HARD   = HRTIMER_MODE_REL | HRTIMER_MODE_HARD,
+
+       HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD,
+       HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD,
 };
 
 /*
@@ -87,6 +110,7 @@ enum hrtimer_restart {
  * @base:      pointer to the timer base (per cpu and per clock)
  * @state:     state information (See bit values above)
  * @is_rel:    Set if the timer was armed relative
+ * @is_soft:   Set if hrtimer will be expired in soft interrupt context.
  *
  * The hrtimer structure must be initialized by hrtimer_init()
  */
@@ -97,6 +121,7 @@ struct hrtimer {
        struct hrtimer_clock_base       *base;
        u8                              state;
        u8                              is_rel;
+       u8                              is_soft;
 };
 
 /**
@@ -112,9 +137,9 @@ struct hrtimer_sleeper {
 };
 
 #ifdef CONFIG_64BIT
-# define HRTIMER_CLOCK_BASE_ALIGN      64
+# define __hrtimer_clock_base_align    ____cacheline_aligned
 #else
-# define HRTIMER_CLOCK_BASE_ALIGN      32
+# define __hrtimer_clock_base_align
 #endif
 
 /**
@@ -123,48 +148,57 @@ struct hrtimer_sleeper {
  * @index:             clock type index for per_cpu support when moving a
  *                     timer to a base on another cpu.
  * @clockid:           clock id for per_cpu support
+ * @seq:               seqcount around __run_hrtimer
+ * @running:           pointer to the currently running hrtimer
  * @active:            red black tree root node for the active timers
  * @get_time:          function to retrieve the current time of the clock
  * @offset:            offset of this clock to the monotonic base
  */
 struct hrtimer_clock_base {
        struct hrtimer_cpu_base *cpu_base;
-       int                     index;
+       unsigned int            index;
        clockid_t               clockid;
+       seqcount_t              seq;
+       struct hrtimer          *running;
        struct timerqueue_head  active;
        ktime_t                 (*get_time)(void);
        ktime_t                 offset;
-} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
+} __hrtimer_clock_base_align;
 
 enum  hrtimer_base_type {
        HRTIMER_BASE_MONOTONIC,
        HRTIMER_BASE_REALTIME,
        HRTIMER_BASE_BOOTTIME,
        HRTIMER_BASE_TAI,
+       HRTIMER_BASE_MONOTONIC_SOFT,
+       HRTIMER_BASE_REALTIME_SOFT,
+       HRTIMER_BASE_BOOTTIME_SOFT,
+       HRTIMER_BASE_TAI_SOFT,
        HRTIMER_MAX_CLOCK_BASES,
 };
 
-/*
+/**
  * struct hrtimer_cpu_base - the per cpu clock bases
  * @lock:              lock protecting the base and associated clock bases
  *                     and timers
- * @seq:               seqcount around __run_hrtimer
- * @running:           pointer to the currently running hrtimer
  * @cpu:               cpu number
  * @active_bases:      Bitfield to mark bases with active timers
  * @clock_was_set_seq: Sequence counter of clock was set events
- * @migration_enabled: The migration of hrtimers to other cpus is enabled
- * @nohz_active:       The nohz functionality is enabled
- * @expires_next:      absolute time of the next event which was scheduled
- *                     via clock_set_next_event()
- * @next_timer:                Pointer to the first expiring timer
- * @in_hrtirq:         hrtimer_interrupt() is currently executing
  * @hres_active:       State of high resolution mode
+ * @in_hrtirq:         hrtimer_interrupt() is currently executing
  * @hang_detected:     The last hrtimer interrupt detected a hang
+ * @softirq_activated: displays, if the softirq is raised - update of softirq
+ *                     related settings is not required then.
  * @nr_events:         Total number of hrtimer interrupt events
  * @nr_retries:                Total number of hrtimer interrupt retries
  * @nr_hangs:          Total number of hrtimer interrupt hangs
  * @max_hang_time:     Maximum time spent in hrtimer_interrupt
+ * @expires_next:      absolute time of the next event, is required for remote
+ *                     hrtimer enqueue; it is the total first expiry time (hard
+ *                     and soft hrtimer are taken into account)
+ * @next_timer:                Pointer to the first expiring timer
+ * @softirq_expires_next: Time to check, if soft queues needs also to be expired
+ * @softirq_next_timer: Pointer to the first expiring softirq based timer
  * @clock_base:                array of clock bases for this cpu
  *
  * Note: next_timer is just an optimization for __remove_hrtimer().
@@ -173,31 +207,31 @@ enum  hrtimer_base_type {
  */
 struct hrtimer_cpu_base {
        raw_spinlock_t                  lock;
-       seqcount_t                      seq;
-       struct hrtimer                  *running;
        unsigned int                    cpu;
        unsigned int                    active_bases;
        unsigned int                    clock_was_set_seq;
-       bool                            migration_enabled;
-       bool                            nohz_active;
+       unsigned int                    hres_active             : 1,
+                                       in_hrtirq               : 1,
+                                       hang_detected           : 1,
+                                       softirq_activated       : 1;
 #ifdef CONFIG_HIGH_RES_TIMERS
-       unsigned int                    in_hrtirq       : 1,
-                                       hres_active     : 1,
-                                       hang_detected   : 1;
-       ktime_t                         expires_next;
-       struct hrtimer                  *next_timer;
        unsigned int                    nr_events;
-       unsigned int                    nr_retries;
-       unsigned int                    nr_hangs;
+       unsigned short                  nr_retries;
+       unsigned short                  nr_hangs;
        unsigned int                    max_hang_time;
 #endif
+       ktime_t                         expires_next;
+       struct hrtimer                  *next_timer;
+       ktime_t                         softirq_expires_next;
+#ifdef CONFIG_PREEMPT_RT_BASE
+       wait_queue_head_t               wait;
+#endif
+       struct hrtimer                  *softirq_next_timer;
        struct hrtimer_clock_base       clock_base[HRTIMER_MAX_CLOCK_BASES];
 } ____cacheline_aligned;
 
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
-       BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
-
        timer->node.expires = time;
        timer->_softexpires = time;
 }
@@ -266,16 +300,17 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
        return timer->base->get_time();
 }
 
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+       return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+               timer->base->cpu_base->hres_active : 0;
+}
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 struct clock_event_device;
 
 extern void hrtimer_interrupt(struct clock_event_device *dev);
 
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
-       return timer->base->cpu_base->hres_active;
-}
-
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -298,11 +333,6 @@ extern unsigned int hrtimer_resolution;
 
 #define hrtimer_resolution     (unsigned int)LOW_RES_NSEC
 
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
-       return 0;
-}
-
 static inline void clock_was_set_delayed(void) { }
 
 #endif
@@ -344,10 +374,17 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 /* Initialize timers: */
 extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock,
                         enum hrtimer_mode mode);
+extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
+                                enum hrtimer_mode mode,
+                                struct task_struct *task);
 
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
 extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock,
                                  enum hrtimer_mode mode);
+extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+                                         clockid_t clock_id,
+                                         enum hrtimer_mode mode,
+                                         struct task_struct *task);
 
 extern void destroy_hrtimer_on_stack(struct hrtimer *timer);
 #else
@@ -357,6 +394,15 @@ static inline void hrtimer_init_on_stack(struct hrtimer *timer,
 {
        hrtimer_init(timer, which_clock, mode);
 }
+
+static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+                                           clockid_t clock_id,
+                                           enum hrtimer_mode mode,
+                                           struct task_struct *task)
+{
+       hrtimer_init_sleeper(sl, clock_id, mode, task);
+}
+
 static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 #endif
 
@@ -365,11 +411,12 @@ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
                                   u64 range_ns, const enum hrtimer_mode mode);
 
 /**
- * hrtimer_start - (re)start an hrtimer on the current CPU
+ * hrtimer_start - (re)start an hrtimer
  * @timer:     the timer to be added
  * @tim:       expiry time
- * @mode:      expiry mode: absolute (HRTIMER_MODE_ABS) or
- *             relative (HRTIMER_MODE_REL)
+ * @mode:      timer mode: absolute (HRTIMER_MODE_ABS) or
+ *             relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
+ *             softirq based mode is considered for debug purpose only!
  */
 static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
                                 const enum hrtimer_mode mode)
@@ -396,6 +443,13 @@ static inline void hrtimer_restart(struct hrtimer *timer)
        hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/* Softirq preemption could deadlock timer removal */
+#ifdef CONFIG_PREEMPT_RT_BASE
+  extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
+#else
+# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0)
+#endif
+
 /* Query timers: */
 extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
 
@@ -420,9 +474,9 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
  * Helper function to check, whether the timer is running the callback
  * function
  */
-static inline int hrtimer_callback_running(struct hrtimer *timer)
+static inline int hrtimer_callback_running(const struct hrtimer *timer)
 {
-       return timer->base->cpu_base->running == timer;
+       return timer->base->running == timer;
 }
 
 /* Forward a hrtimer so it expires after now: */
@@ -458,15 +512,12 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp,
                              const enum hrtimer_mode mode,
                              const clockid_t clockid);
 
-extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
-                                struct task_struct *tsk);
-
 extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
                                                const enum hrtimer_mode mode);
 extern int schedule_hrtimeout_range_clock(ktime_t *expires,
                                          u64 delta,
                                          const enum hrtimer_mode mode,
-                                         int clock);
+                                         clockid_t clock_id);
 extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 7c3a365f7e12..a922d984d9b6 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -167,10 +167,7 @@ static inline bool idr_is_empty(const struct idr *idr)
  * Each idr_preload() should be matched with an invocation of this
  * function.  See idr_preload() for details.
  */
-static inline void idr_preload_end(void)
-{
-       preempt_enable();
-}
+void idr_preload_end(void);
 
 /**
  * idr_find - return pointer for given id
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 8062e6cc607c..ee3ff961b84c 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -163,6 +163,12 @@ extern struct cred init_cred;
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
+#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE)
+# define INIT_TIMER_LIST               .posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)                                               \
        .vtime.seqcount = SEQCNT_ZERO(tsk.vtime.seqcount),              \
@@ -234,7 +240,8 @@ extern struct cred init_cred;
        .static_prio    = MAX_PRIO-20,                                  \
        .normal_prio    = MAX_PRIO-20,                                  \
        .policy         = SCHED_NORMAL,                                 \
-       .cpus_allowed   = CPU_MASK_ALL,                                 \
+       .cpus_ptr       = &tsk.cpus_mask,                               \
+       .cpus_mask      = CPU_MASK_ALL,                                 \
        .nr_cpus_allowed= NR_CPUS,                                      \
        .mm             = NULL,                                         \
        .active_mm      = &init_mm,                                     \
@@ -276,6 +283,7 @@ extern struct cred init_cred;
        INIT_CPU_TIMERS(tsk)                                            \
        .pi_lock        = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock),        \
        .timer_slack_ns = 50000, /* 50 usec default slack */            \
+       INIT_TIMER_LIST                                                 \
        .pids = {                                                       \
                [PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),            \
                [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),           \
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 69c238210325..0f25fa19b2d8 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -15,6 +15,7 @@
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
+#include <linux/swork.h>
 
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
@@ -63,6 +64,7 @@
  *                interrupt handler after suspending interrupts. For system
  *                wakeup devices users need to implement wakeup detection in
  *                their interrupt handlers.
+ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT)
  */
 #define IRQF_SHARED            0x00000080
 #define IRQF_PROBE_SHARED      0x00000100
@@ -76,6 +78,7 @@
 #define IRQF_NO_THREAD         0x00010000
 #define IRQF_EARLY_RESUME      0x00020000
 #define IRQF_COND_SUSPEND      0x00040000
+#define IRQF_NO_SOFTIRQ_CALL   0x00080000
 
 #define IRQF_TIMER             (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
@@ -207,7 +210,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 #ifdef CONFIG_LOCKDEP
 # define local_irq_enable_in_hardirq() do { } while (0)
 #else
-# define local_irq_enable_in_hardirq() local_irq_enable()
+# define local_irq_enable_in_hardirq() local_irq_enable_nort()
 #endif
 
 extern void disable_irq_nosync(unsigned int irq);
@@ -227,6 +230,7 @@ extern void resume_device_irqs(void);
  * struct irq_affinity_notify - context for notification of IRQ affinity changes
  * @irq:               Interrupt to which notification applies
  * @kref:              Reference count, for internal use
+ * @swork:             Swork item, for internal use
  * @work:              Work item, for internal use
  * @notify:            Function to be called on change.  This will be
  *                     called in process context.
@@ -238,7 +242,11 @@ extern void resume_device_irqs(void);
 struct irq_affinity_notify {
        unsigned int irq;
        struct kref kref;
+#ifdef CONFIG_PREEMPT_RT_BASE
+       struct swork_event swork;
+#else
        struct work_struct work;
+#endif
        void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
        void (*release)(struct kref *ref);
 };
@@ -429,9 +437,13 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
                                 bool state);
 
 #ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
 extern bool force_irqthreads;
+# else
+#  define force_irqthreads     (true)
+# endif
 #else
-#define force_irqthreads       (0)
+#define force_irqthreads       (false)
 #endif
 
 #ifndef __ARCH_SET_SOFTIRQ_PENDING
@@ -488,9 +500,10 @@ struct softirq_action
        void    (*action)(struct softirq_action *);
 };
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
-
+static inline void thread_do_softirq(void) { do_softirq(); }
 #ifdef __ARCH_HAS_DO_SOFTIRQ
 void do_softirq_own_stack(void);
 #else
@@ -499,13 +512,25 @@ static inline void do_softirq_own_stack(void)
        __do_softirq();
 }
 #endif
+#else
+extern void thread_do_softirq(void);
+#endif
 
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 extern void __raise_softirq_irqoff(unsigned int nr);
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void __raise_softirq_irqoff_ksoft(unsigned int nr);
+#else
+static inline void __raise_softirq_irqoff_ksoft(unsigned int nr)
+{
+       __raise_softirq_irqoff(nr);
+}
+#endif
 
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
+extern void softirq_check_pending_idle(void);
 
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
@@ -527,8 +552,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
      to be executed on some cpu at least once after this.
    * If the tasklet is already scheduled, but its execution is still not
      started, it will be executed only once.
-   * If this tasklet is already running on another CPU (or schedule is called
-     from tasklet itself), it is rescheduled for later.
+   * If this tasklet is already running on another CPU, it is rescheduled
+     for later.
+   * Schedule must not be called from the tasklet itself (a lockup occurs)
    * Tasklet is strictly serialized wrt itself, but not
      wrt another tasklets. If client needs some intertask synchronization,
      he makes it with spinlocks.
@@ -553,27 +579,36 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }
 enum
 {
        TASKLET_STATE_SCHED,    /* Tasklet is scheduled for execution */
-       TASKLET_STATE_RUN       /* Tasklet is running (SMP only) */
+       TASKLET_STATE_RUN,      /* Tasklet is running (SMP only) */
+       TASKLET_STATE_PENDING   /* Tasklet is pending */
 };
 
-#ifdef CONFIG_SMP
+#define TASKLET_STATEF_SCHED   (1 << TASKLET_STATE_SCHED)
+#define TASKLET_STATEF_RUN     (1 << TASKLET_STATE_RUN)
+#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING)
+
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
 static inline int tasklet_trylock(struct tasklet_struct *t)
 {
        return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
 }
 
+static inline int tasklet_tryunlock(struct tasklet_struct *t)
+{
+       return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN;
+}
+
 static inline void tasklet_unlock(struct tasklet_struct *t)
 {
        smp_mb__before_atomic();
        clear_bit(TASKLET_STATE_RUN, &(t)->state);
 }
 
-static inline void tasklet_unlock_wait(struct tasklet_struct *t)
-{
-       while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
-}
+extern void tasklet_unlock_wait(struct tasklet_struct *t);
+
 #else
 #define tasklet_trylock(t) 1
+#define tasklet_tryunlock(t)   1
 #define tasklet_unlock_wait(t) do { } while (0)
 #define tasklet_unlock(t) do { } while (0)
 #endif
@@ -607,41 +642,17 @@ static inline void tasklet_disable(struct tasklet_struct *t)
        smp_mb();
 }
 
-static inline void tasklet_enable(struct tasklet_struct *t)
-{
-       smp_mb__before_atomic();
-       atomic_dec(&t->count);
-}
-
+extern void tasklet_enable(struct tasklet_struct *t);
 extern void tasklet_kill(struct tasklet_struct *t);
 extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
                         void (*func)(unsigned long), unsigned long data);
 
-struct tasklet_hrtimer {
-       struct hrtimer          timer;
-       struct tasklet_struct   tasklet;
-       enum hrtimer_restart    (*function)(struct hrtimer *);
-};
-
-extern void
-tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-                    enum hrtimer_restart (*function)(struct hrtimer *),
-                    clockid_t which_clock, enum hrtimer_mode mode);
-
-static inline
-void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
-                          const enum hrtimer_mode mode)
-{
-       hrtimer_start(&ttimer->timer, time, mode);
-}
-
-static inline
-void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
-{
-       hrtimer_cancel(&ttimer->timer);
-       tasklet_kill(&ttimer->tasklet);
-}
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void softirq_early_init(void);
+#else
+static inline void softirq_early_init(void) { }
+#endif
 
 /*
  * Autoprobing for irqs:
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 0d53626405bf..ddd23c6e2e55 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -74,6 +74,7 @@ enum irqchip_irq_state;
  * IRQ_IS_POLLED               - Always polled by another interrupt. Exclude
  *                               it from the spurious interrupt detection
  *                               mechanism and from core side polling.
+ * IRQ_NO_SOFTIRQ_CALL         - No softirq processing in the irq thread context (RT)
  * IRQ_DISABLE_UNLAZY          - Disable lazy irq disable
  */
 enum {
@@ -101,13 +102,14 @@ enum {
        IRQ_PER_CPU_DEVID       = (1 << 17),
        IRQ_IS_POLLED           = (1 << 18),
        IRQ_DISABLE_UNLAZY      = (1 << 19),
+       IRQ_NO_SOFTIRQ_CALL     = (1 << 20),
 };
 
 #define IRQF_MODIFY_MASK       \
        (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
         IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
         IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
-        IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
+        IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL)
 
 #define IRQ_NO_BALANCING_MASK  (IRQ_PER_CPU | IRQ_NO_BALANCING)
 
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 9270d73ea682..1e66fac6f1d2 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -17,6 +17,7 @@
 #define IRQ_WORK_BUSY          2UL
 #define IRQ_WORK_FLAGS         3UL
 #define IRQ_WORK_LAZY          4UL /* Doesn't want IPI, wait for tick */
+#define IRQ_WORK_HARD_IRQ      8UL /* Run hard IRQ context, even on RT */
 
 struct irq_work {
        unsigned long flags;
@@ -52,4 +53,10 @@ static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
 #endif
 
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+void irq_work_tick_soft(void);
+#else
+static inline void irq_work_tick_soft(void) { }
+#endif
+
 #endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index bacb499c512c..688f2565294c 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -568,6 +568,7 @@ struct rdists {
                void __iomem    *rd_base;
                struct page     *pend_page;
                phys_addr_t     phys_base;
+               bool            lpi_enabled;
        } __percpu              *rdist;
        struct page             *prop_page;
        int                     id_bits;
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index b6084898d330..d334476cdca6 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -70,6 +70,7 @@ struct irq_desc {
        unsigned int            irqs_unhandled;
        atomic_t                threads_handled;
        int                     threads_handled_last;
+       u64                     random_ip;
        raw_spinlock_t          lock;
        struct cpumask          *percpu_enabled;
        const struct cpumask    *percpu_affinity;
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 46cb57d5eb13..2e023bfe45af 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -34,16 +34,6 @@ do {                                         \
        current->hardirq_context--;             \
        crossrelease_hist_end(XHLOCK_HARD);     \
 } while (0)
-# define lockdep_softirq_enter()               \
-do {                                           \
-       current->softirq_context++;             \
-       crossrelease_hist_start(XHLOCK_SOFT);   \
-} while (0)
-# define lockdep_softirq_exit()                        \
-do {                                           \
-       current->softirq_context--;             \
-       crossrelease_hist_end(XHLOCK_SOFT);     \
-} while (0)
 # define INIT_TRACE_IRQFLAGS   .softirqs_enabled = 1,
 #else
 # define trace_hardirqs_on()           do { } while (0)
@@ -56,9 +46,23 @@ do {                                         \
 # define trace_softirqs_enabled(p)     0
 # define trace_hardirq_enter()         do { } while (0)
 # define trace_hardirq_exit()          do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+#endif
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL)
+# define lockdep_softirq_enter()               \
+do {                                           \
+       current->softirq_context++;             \
+       crossrelease_hist_start(XHLOCK_SOFT);   \
+} while (0)
+# define lockdep_softirq_exit()                        \
+do {                                           \
+       current->softirq_context--;             \
+       crossrelease_hist_end(XHLOCK_SOFT);     \
+} while (0)
+#else
 # define lockdep_softirq_enter()       do { } while (0)
 # define lockdep_softirq_exit()                do { } while (0)
-# define INIT_TRACE_IRQFLAGS
 #endif
 
 #if defined(CONFIG_IRQSOFF_TRACER) || \
@@ -165,4 +169,23 @@ do {                                               \
 
 #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags)
 
+/*
+ * local_irq* variants depending on RT/!RT
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define local_irq_disable_nort()      do { } while (0)
+# define local_irq_enable_nort()       do { } while (0)
+# define local_irq_save_nort(flags)    local_save_flags(flags)
+# define local_irq_restore_nort(flags) (void)(flags)
+# define local_irq_disable_rt()                local_irq_disable()
+# define local_irq_enable_rt()         local_irq_enable()
+#else
+# define local_irq_disable_nort()      local_irq_disable()
+# define local_irq_enable_nort()       local_irq_enable()
+# define local_irq_save_nort(flags)    local_irq_save(flags)
+# define local_irq_restore_nort(flags) local_irq_restore(flags)
+# define local_irq_disable_rt()                do { } while (0)
+# define local_irq_enable_rt()         do { } while (0)
+#endif
+
 #endif
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 29290bfb94a8..32379bfab9f0 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -347,32 +347,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh)
 
 static inline void jbd_lock_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        bit_spin_lock(BH_State, &bh->b_state);
+#else
+       spin_lock(&bh->b_state_lock);
+#endif
 }
 
 static inline int jbd_trylock_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        return bit_spin_trylock(BH_State, &bh->b_state);
+#else
+       return spin_trylock(&bh->b_state_lock);
+#endif
 }
 
 static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        return bit_spin_is_locked(BH_State, &bh->b_state);
+#else
+       return spin_is_locked(&bh->b_state_lock);
+#endif
 }
 
 static inline void jbd_unlock_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        bit_spin_unlock(BH_State, &bh->b_state);
+#else
+       spin_unlock(&bh->b_state_lock);
+#endif
 }
 
 static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        bit_spin_lock(BH_JournalHead, &bh->b_state);
+#else
+       spin_lock(&bh->b_journal_head_lock);
+#endif
 }
 
 static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        bit_spin_unlock(BH_JournalHead, &bh->b_state);
+#else
+       spin_unlock(&bh->b_journal_head_lock);
+#endif
 }
 
 #define J_ASSERT(assert)       BUG_ON(!(assert))
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 68bd88223417..e033b25b0b72 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt,
 extern __printf(1, 2) int kdb_printf(const char *, ...);
 typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...);
 
+#define in_kdb_printk()        (kdb_trap_printk)
 extern void kdb_init(int level);
 
 /* Access to kdb specific polling devices */
@@ -201,6 +202,7 @@ extern int kdb_register_flags(char *, kdb_func_t, char *, char *,
 extern int kdb_unregister(char *);
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
+#define in_kdb_printk() (0)
 static inline void kdb_init(int level) {}
 static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
                               char *help, short minlen) { return 0; }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4b484ab9e163..74feebf9d82c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -225,6 +225,9 @@ extern int _cond_resched(void);
  */
 # define might_sleep() \
        do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+
+# define might_sleep_no_state_check() \
+       do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
 # define sched_annotate_sleep()        (current->task_state_change = 0)
 #else
   static inline void ___might_sleep(const char *file, int line,
@@ -232,6 +235,7 @@ extern int _cond_resched(void);
   static inline void __might_sleep(const char *file, int line,
                                   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
+# define might_sleep_no_state_check() do { might_resched(); } while (0)
 # define sched_annotate_sleep() do { } while (0)
 #endif
 
@@ -531,6 +535,7 @@ extern enum system_states {
        SYSTEM_HALT,
        SYSTEM_POWER_OFF,
        SYSTEM_RESTART,
+       SYSTEM_SUSPEND,
 } system_state;
 
 #define TAINT_PROPRIETARY_MODULE       0
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index 3fc2cc57ba1b..0b5de7d9ffcf 100644
--- a/include/linux/list_bl.h
+++ b/include/linux/list_bl.h
@@ -3,6 +3,7 @@
 #define _LINUX_LIST_BL_H
 
 #include <linux/list.h>
+#include <linux/spinlock.h>
 #include <linux/bit_spinlock.h>
 
 /*
@@ -33,13 +34,24 @@
 
 struct hlist_bl_head {
        struct hlist_bl_node *first;
+#ifdef CONFIG_PREEMPT_RT_BASE
+       raw_spinlock_t lock;
+#endif
 };
 
 struct hlist_bl_node {
        struct hlist_bl_node *next, **pprev;
 };
-#define INIT_HLIST_BL_HEAD(ptr) \
-       ((ptr)->first = NULL)
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+#define INIT_HLIST_BL_HEAD(h)          \
+do {                                   \
+       (h)->first = NULL;              \
+       raw_spin_lock_init(&(h)->lock); \
+} while (0)
+#else
+#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL
+#endif
 
 static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
 {
@@ -119,12 +131,26 @@ static inline void hlist_bl_del_init(struct hlist_bl_node *n)
 
 static inline void hlist_bl_lock(struct hlist_bl_head *b)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        bit_spin_lock(0, (unsigned long *)b);
+#else
+       raw_spin_lock(&b->lock);
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+       __set_bit(0, (unsigned long *)b);
+#endif
+#endif
 }
 
 static inline void hlist_bl_unlock(struct hlist_bl_head *b)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
        __bit_spin_unlock(0, (unsigned long *)b);
+#else
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+       __clear_bit(0, (unsigned long *)b);
+#endif
+       raw_spin_unlock(&b->lock);
+#endif
 }
 
 static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)
diff --git a/include/linux/locallock.h b/include/linux/locallock.h
new file mode 100644
index 000000000000..921eab83cd34
--- /dev/null
+++ b/include/linux/locallock.h
@@ -0,0 +1,281 @@
+#ifndef _LINUX_LOCALLOCK_H
+#define _LINUX_LOCALLOCK_H
+
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+# define LL_WARN(cond) WARN_ON(cond)
+#else
+# define LL_WARN(cond) do { } while (0)
+#endif
+
+/*
+ * per cpu lock based substitute for local_irq_*()
+ */
+struct local_irq_lock {
+       spinlock_t              lock;
+       struct task_struct      *owner;
+       int                     nestcnt;
+       unsigned long           flags;
+};
+
+#define DEFINE_LOCAL_IRQ_LOCK(lvar)                                    \
+       DEFINE_PER_CPU(struct local_irq_lock, lvar) = {                 \
+               .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) }
+
+#define DECLARE_LOCAL_IRQ_LOCK(lvar)                                   \
+       DECLARE_PER_CPU(struct local_irq_lock, lvar)
+
+#define local_irq_lock_init(lvar)                                      \
+       do {                                                            \
+               int __cpu;                                              \
+               for_each_possible_cpu(__cpu)                            \
+                       spin_lock_init(&per_cpu(lvar, __cpu).lock);     \
+       } while (0)
+
+static inline void __local_lock(struct local_irq_lock *lv)
+{
+       if (lv->owner != current) {
+               spin_lock(&lv->lock);
+               LL_WARN(lv->owner);
+               LL_WARN(lv->nestcnt);
+               lv->owner = current;
+       }
+       lv->nestcnt++;
+}
+
+#define local_lock(lvar)                                       \
+       do { __local_lock(&get_local_var(lvar)); } while (0)
+
+#define local_lock_on(lvar, cpu)                               \
+       do { __local_lock(&per_cpu(lvar, cpu)); } while (0)
+
+static inline int __local_trylock(struct local_irq_lock *lv)
+{
+       if (lv->owner != current && spin_trylock(&lv->lock)) {
+               LL_WARN(lv->owner);
+               LL_WARN(lv->nestcnt);
+               lv->owner = current;
+               lv->nestcnt = 1;
+               return 1;
+       } else if (lv->owner == current) {
+               lv->nestcnt++;
+               return 1;
+       }
+       return 0;
+}
+
+#define local_trylock(lvar)                                            \
+       ({                                                              \
+               int __locked;                                           \
+               __locked = __local_trylock(&get_local_var(lvar));       \
+               if (!__locked)                                          \
+                       put_local_var(lvar);                            \
+               __locked;                                               \
+       })
+
+static inline void __local_unlock(struct local_irq_lock *lv)
+{
+       LL_WARN(lv->nestcnt == 0);
+       LL_WARN(lv->owner != current);
+       if (--lv->nestcnt)
+               return;
+
+       lv->owner = NULL;
+       spin_unlock(&lv->lock);
+}
+
+#define local_unlock(lvar)                                     \
+       do {                                                    \
+               __local_unlock(this_cpu_ptr(&lvar));            \
+               put_local_var(lvar);                            \
+       } while (0)
+
+#define local_unlock_on(lvar, cpu)                       \
+       do { __local_unlock(&per_cpu(lvar, cpu)); } while (0)
+
+static inline void __local_lock_irq(struct local_irq_lock *lv)
+{
+       spin_lock_irqsave(&lv->lock, lv->flags);
+       LL_WARN(lv->owner);
+       LL_WARN(lv->nestcnt);
+       lv->owner = current;
+       lv->nestcnt = 1;
+}
+
+#define local_lock_irq(lvar)                                           \
+       do { __local_lock_irq(&get_local_var(lvar)); } while (0)
+
+#define local_lock_irq_on(lvar, cpu)                                   \
+       do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0)
+
+static inline void __local_unlock_irq(struct local_irq_lock *lv)
+{
+       LL_WARN(!lv->nestcnt);
+       LL_WARN(lv->owner != current);
+       lv->owner = NULL;
+       lv->nestcnt = 0;
+       spin_unlock_irq(&lv->lock);
+}
+
+#define local_unlock_irq(lvar)                                         \
+       do {                                                            \
+               __local_unlock_irq(this_cpu_ptr(&lvar));                \
+               put_local_var(lvar);                                    \
+       } while (0)
+
+#define local_unlock_irq_on(lvar, cpu)                                 \
+       do {                                                            \
+               __local_unlock_irq(&per_cpu(lvar, cpu));                \
+       } while (0)
+
+static inline int __local_lock_irqsave(struct local_irq_lock *lv)
+{
+       if (lv->owner != current) {
+               __local_lock_irq(lv);
+               return 0;
+       } else {
+               lv->nestcnt++;
+               return 1;
+       }
+}
+
+#define local_lock_irqsave(lvar, _flags)                               \
+       do {                                                            \
+               if (__local_lock_irqsave(&get_local_var(lvar)))         \
+                       put_local_var(lvar);                            \
+               _flags = __this_cpu_read(lvar.flags);                   \
+       } while (0)
+
+#define local_lock_irqsave_on(lvar, _flags, cpu)                       \
+       do {                                                            \
+               __local_lock_irqsave(&per_cpu(lvar, cpu));              \
+               _flags = per_cpu(lvar, cpu).flags;                      \
+       } while (0)
+
+static inline int __local_unlock_irqrestore(struct local_irq_lock *lv,
+                                           unsigned long flags)
+{
+       LL_WARN(!lv->nestcnt);
+       LL_WARN(lv->owner != current);
+       if (--lv->nestcnt)
+               return 0;
+
+       lv->owner = NULL;
+       spin_unlock_irqrestore(&lv->lock, lv->flags);
+       return 1;
+}
+
+#define local_unlock_irqrestore(lvar, flags)                           \
+       do {                                                            \
+               if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \
+                       put_local_var(lvar);                            \
+       } while (0)
+
+#define local_unlock_irqrestore_on(lvar, flags, cpu)                   \
+       do {                                                            \
+               __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags);  \
+       } while (0)
+
+#define local_spin_trylock_irq(lvar, lock)                             \
+       ({                                                              \
+               int __locked;                                           \
+               local_lock_irq(lvar);                                   \
+               __locked = spin_trylock(lock);                          \
+               if (!__locked)                                          \
+                       local_unlock_irq(lvar);                         \
+               __locked;                                               \
+       })
+
+#define local_spin_lock_irq(lvar, lock)                                        \
+       do {                                                            \
+               local_lock_irq(lvar);                                   \
+               spin_lock(lock);                                        \
+       } while (0)
+
+#define local_spin_unlock_irq(lvar, lock)                              \
+       do {                                                            \
+               spin_unlock(lock);                                      \
+               local_unlock_irq(lvar);                                 \
+       } while (0)
+
+#define local_spin_lock_irqsave(lvar, lock, flags)                     \
+       do {                                                            \
+               local_lock_irqsave(lvar, flags);                        \
+               spin_lock(lock);                                        \
+       } while (0)
+
+#define local_spin_unlock_irqrestore(lvar, lock, flags)                        \
+       do {                                                            \
+               spin_unlock(lock);                                      \
+               local_unlock_irqrestore(lvar, flags);                   \
+       } while (0)
+
+#define get_locked_var(lvar, var)                                      \
+       (*({                                                            \
+               local_lock(lvar);                                       \
+               this_cpu_ptr(&var);                                     \
+       }))
+
+#define put_locked_var(lvar, var)      local_unlock(lvar);
+
+#define get_locked_ptr(lvar, var)                                      \
+       ({                                                              \
+               local_lock(lvar);                                       \
+               this_cpu_ptr(var);                                      \
+       })
+
+#define put_locked_ptr(lvar, var)      local_unlock(lvar);
+
+#define local_lock_cpu(lvar)                                           \
+       ({                                                              \
+               local_lock(lvar);                                       \
+               smp_processor_id();                                     \
+       })
+
+#define local_unlock_cpu(lvar)                 local_unlock(lvar)
+
+#else /* PREEMPT_RT_BASE */
+
+#define DEFINE_LOCAL_IRQ_LOCK(lvar)            __typeof__(const int) lvar
+#define DECLARE_LOCAL_IRQ_LOCK(lvar)           extern __typeof__(const int) lvar
+
+static inline void local_irq_lock_init(int lvar) { }
+
+#define local_trylock(lvar)                                    \
+       ({                                                      \
+               preempt_disable();                              \
+               1;                                              \
+       })
+
+#define local_lock(lvar)                       preempt_disable()
+#define local_unlock(lvar)                     preempt_enable()
+#define local_lock_irq(lvar)                   local_irq_disable()
+#define local_lock_irq_on(lvar, cpu)           local_irq_disable()
+#define local_unlock_irq(lvar)                 local_irq_enable()
+#define local_unlock_irq_on(lvar, cpu)         local_irq_enable()
+#define local_lock_irqsave(lvar, flags)                local_irq_save(flags)
+#define local_unlock_irqrestore(lvar, flags)   local_irq_restore(flags)
+
+#define local_spin_trylock_irq(lvar, lock)     spin_trylock_irq(lock)
+#define local_spin_lock_irq(lvar, lock)                spin_lock_irq(lock)
+#define local_spin_unlock_irq(lvar, lock)      spin_unlock_irq(lock)
+#define local_spin_lock_irqsave(lvar, lock, flags)     \
+       spin_lock_irqsave(lock, flags)
+#define local_spin_unlock_irqrestore(lvar, lock, flags)        \
+       spin_unlock_irqrestore(lock, flags)
+
+#define get_locked_var(lvar, var)              get_cpu_var(var)
+#define put_locked_var(lvar, var)              put_cpu_var(var)
+#define get_locked_ptr(lvar, var)              get_cpu_ptr(var)
+#define put_locked_ptr(lvar, var)              put_cpu_ptr(var)
+
+#define local_lock_cpu(lvar)                   get_cpu()
+#define local_unlock_cpu(lvar)                 put_cpu()
+
+#endif
+
+#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e41ef532c4ce..63317710311e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -12,6 +12,7 @@
 #include <linux/completion.h>
 #include <linux/cpumask.h>
 #include <linux/uprobes.h>
+#include <linux/rcupdate.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
 
@@ -496,6 +497,9 @@ struct mm_struct {
        bool tlb_flush_batched;
 #endif
        struct uprobes_state uprobes_state;
+#ifdef CONFIG_PREEMPT_RT_BASE
+       struct rcu_head delayed_drop;
+#endif
 #ifdef CONFIG_HUGETLB_PAGE
        atomic_long_t hugetlb_usage;
 #endif
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 153274f78402..dbb52857b25b 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -23,6 +23,17 @@
 
 struct ww_acquire_ctx;
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
+               , .dep_map = { .name = #lockname }
+#else
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
+#endif
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/mutex_rt.h>
+#else
+
 /*
  * Simple, straightforward mutexes with strict semantics:
  *
@@ -114,13 +125,6 @@ do {                                                                       \
        __mutex_init((mutex), #mutex, &__key);                          \
 } while (0)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
-               , .dep_map = { .name = #lockname }
-#else
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
-#endif
-
 #define __MUTEX_INITIALIZER(lockname) \
                { .owner = ATOMIC_LONG_INIT(0) \
                , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
@@ -228,4 +232,6 @@ mutex_trylock_recursive(struct mutex *lock)
        return mutex_trylock(lock);
 }
 
+#endif /* !PREEMPT_RT_FULL */
+
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h
new file mode 100644
index 000000000000..3fcb5edb1d2b
--- /dev/null
+++ b/include/linux/mutex_rt.h
@@ -0,0 +1,130 @@
+#ifndef __LINUX_MUTEX_RT_H
+#define __LINUX_MUTEX_RT_H
+
+#ifndef __LINUX_MUTEX_H
+#error "Please include mutex.h"
+#endif
+
+#include <linux/rtmutex.h>
+
+/* FIXME: Just for __lockfunc */
+#include <linux/spinlock.h>
+
+struct mutex {
+       struct rt_mutex         lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       struct lockdep_map      dep_map;
+#endif
+};
+
+#define __MUTEX_INITIALIZER(mutexname)                                 \
+       {                                                               \
+               .lock = __RT_MUTEX_INITIALIZER(mutexname.lock)          \
+               __DEP_MAP_MUTEX_INITIALIZER(mutexname)                  \
+       }
+
+#define DEFINE_MUTEX(mutexname)                                                \
+       struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
+
+extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key);
+extern void __lockfunc _mutex_lock(struct mutex *lock);
+extern void __lockfunc _mutex_lock_io(struct mutex *lock);
+extern void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass);
+extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock);
+extern int __lockfunc _mutex_lock_killable(struct mutex *lock);
+extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass);
+extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
+extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass);
+extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass);
+extern int __lockfunc _mutex_trylock(struct mutex *lock);
+extern void __lockfunc _mutex_unlock(struct mutex *lock);
+
+#define mutex_is_locked(l)             rt_mutex_is_locked(&(l)->lock)
+#define mutex_lock(l)                  _mutex_lock(l)
+#define mutex_lock_interruptible(l)    _mutex_lock_interruptible(l)
+#define mutex_lock_killable(l)         _mutex_lock_killable(l)
+#define mutex_trylock(l)               _mutex_trylock(l)
+#define mutex_unlock(l)                        _mutex_unlock(l)
+#define mutex_lock_io(l)               _mutex_lock_io(l);
+
+#define __mutex_owner(l)               ((l)->lock.owner)
+
+#ifdef CONFIG_DEBUG_MUTEXES
+#define mutex_destroy(l)               rt_mutex_destroy(&(l)->lock)
+#else
+static inline void mutex_destroy(struct mutex *lock) {}
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define mutex_lock_nested(l, s)       _mutex_lock_nested(l, s)
+# define mutex_lock_interruptible_nested(l, s) \
+                                       _mutex_lock_interruptible_nested(l, s)
+# define mutex_lock_killable_nested(l, s) \
+                                       _mutex_lock_killable_nested(l, s)
+# define mutex_lock_io_nested(l, s)    _mutex_lock_io_nested(l, s)
+
+# define mutex_lock_nest_lock(lock, nest_lock)                         \
+do {                                                                   \
+       typecheck(struct lockdep_map *, &(nest_lock)->dep_map);         \
+       _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);             \
+} while (0)
+
+#else
+# define mutex_lock_nested(l, s)       _mutex_lock(l)
+# define mutex_lock_interruptible_nested(l, s) \
+                                       _mutex_lock_interruptible(l)
+# define mutex_lock_killable_nested(l, s) \
+                                       _mutex_lock_killable(l)
+# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
+# define mutex_lock_io_nested(l, s)    _mutex_lock_io(l)
+#endif
+
+# define mutex_init(mutex)                             \
+do {                                                   \
+       static struct lock_class_key __key;             \
+                                                       \
+       rt_mutex_init(&(mutex)->lock);                  \
+       __mutex_do_init((mutex), #mutex, &__key);       \
+} while (0)
+
+# define __mutex_init(mutex, name, key)                        \
+do {                                                   \
+       rt_mutex_init(&(mutex)->lock);                  \
+       __mutex_do_init((mutex), name, key);            \
+} while (0)
+
+/**
+ * These values are chosen such that FAIL and SUCCESS match the
+ * values of the regular mutex_trylock().
+ */
+enum mutex_trylock_recursive_enum {
+       MUTEX_TRYLOCK_FAILED    = 0,
+       MUTEX_TRYLOCK_SUCCESS   = 1,
+       MUTEX_TRYLOCK_RECURSIVE,
+};
+/**
+ * mutex_trylock_recursive - trylock variant that allows recursive locking
+ * @lock: mutex to be locked
+ *
+ * This function should not be used, _ever_. It is purely for hysterical GEM
+ * raisins, and once those are gone this will be removed.
+ *
+ * Returns:
+ *  MUTEX_TRYLOCK_FAILED    - trylock failed,
+ *  MUTEX_TRYLOCK_SUCCESS   - lock acquired,
+ *  MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
+ */
+int __rt_mutex_owner_current(struct rt_mutex *lock);
+
+static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
+mutex_trylock_recursive(struct mutex *lock)
+{
+       if (unlikely(__rt_mutex_owner_current(&lock->lock)))
+               return MUTEX_TRYLOCK_RECURSIVE;
+
+       return mutex_trylock(lock);
+}
+
+extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
+
+#endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a516dbe5869f..3ceccf72757e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -409,7 +409,19 @@ typedef enum rx_handler_result rx_handler_result_t;
 typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
 
 void __napi_schedule(struct napi_struct *n);
+
+/*
+ * When PREEMPT_RT_FULL is defined, all device interrupt handlers
+ * run as threads, and they can also be preempted (without PREEMPT_RT
+ * interrupt threads can not be preempted). Which means that calling
+ * __napi_schedule_irqoff() from an interrupt handler can be preempted
+ * and can corrupt the napi->poll_list.
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define __napi_schedule_irqoff(n) __napi_schedule(n)
+#else
 void __napi_schedule_irqoff(struct napi_struct *n);
+#endif
 
 static inline bool napi_disable_pending(struct napi_struct *n)
 {
@@ -571,7 +583,11 @@ struct netdev_queue {
  * write-mostly part
  */
        spinlock_t              _xmit_lock ____cacheline_aligned_in_smp;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct task_struct      *xmit_lock_owner;
+#else
        int                     xmit_lock_owner;
+#endif
        /*
         * Time (in jiffies) of last Tx
         */
@@ -2440,14 +2456,53 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
-DECLARE_PER_CPU(int, xmit_recursion);
 #define XMIT_RECURSION_LIMIT   10
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int dev_recursion_level(void)
+{
+       return current->xmit_recursion;
+}
+
+static inline int xmit_rec_read(void)
+{
+       return current->xmit_recursion;
+}
+
+static inline void xmit_rec_inc(void)
+{
+       current->xmit_recursion++;
+}
+
+static inline void xmit_rec_dec(void)
+{
+       current->xmit_recursion--;
+}
+
+#else
+
+DECLARE_PER_CPU(int, xmit_recursion);
 
 static inline int dev_recursion_level(void)
 {
        return this_cpu_read(xmit_recursion);
 }
 
+static inline int xmit_rec_read(void)
+{
+       return __this_cpu_read(xmit_recursion);
+}
+
+static inline void xmit_rec_inc(void)
+{
+       __this_cpu_inc(xmit_recursion);
+}
+
+static inline void xmit_rec_dec(void)
+{
+       __this_cpu_dec(xmit_recursion);
+}
+#endif
+
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
@@ -2799,6 +2854,7 @@ struct softnet_data {
        unsigned int            dropped;
        struct sk_buff_head     input_pkt_queue;
        struct napi_struct      backlog;
+       struct sk_buff_head     tofree_queue;
 
 };
 
@@ -3522,10 +3578,48 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
        return (1 << debug_value) - 1;
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu)
+{
+       txq->xmit_lock_owner = current;
+}
+
+static inline void netdev_queue_clear_owner(struct netdev_queue *txq)
+{
+       txq->xmit_lock_owner = NULL;
+}
+
+static inline bool netdev_queue_has_owner(struct netdev_queue *txq)
+{
+       if (txq->xmit_lock_owner != NULL)
+               return true;
+       return false;
+}
+
+#else
+
+static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu)
+{
+       txq->xmit_lock_owner = cpu;
+}
+
+static inline void netdev_queue_clear_owner(struct netdev_queue *txq)
+{
+       txq->xmit_lock_owner = -1;
+}
+
+static inline bool netdev_queue_has_owner(struct netdev_queue *txq)
+{
+       if (txq->xmit_lock_owner != -1)
+               return true;
+       return false;
+}
+#endif
+
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
        spin_lock(&txq->_xmit_lock);
-       txq->xmit_lock_owner = cpu;
+       netdev_queue_set_owner(txq, cpu);
 }
 
 static inline bool __netif_tx_acquire(struct netdev_queue *txq)
@@ -3542,32 +3636,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
        spin_lock_bh(&txq->_xmit_lock);
-       txq->xmit_lock_owner = smp_processor_id();
+       netdev_queue_set_owner(txq, smp_processor_id());
 }
 
 static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 {
        bool ok = spin_trylock(&txq->_xmit_lock);
        if (likely(ok))
-               txq->xmit_lock_owner = smp_processor_id();
+               netdev_queue_set_owner(txq, smp_processor_id());
        return ok;
 }
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-       txq->xmit_lock_owner = -1;
+       netdev_queue_clear_owner(txq);
        spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-       txq->xmit_lock_owner = -1;
+       netdev_queue_clear_owner(txq);
        spin_unlock_bh(&txq->_xmit_lock);
 }
 
 static inline void txq_trans_update(struct netdev_queue *txq)
 {
-       if (txq->xmit_lock_owner != -1)
+       if (netdev_queue_has_owner(txq))
                txq->trans_start = jiffies;
 }
 
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 54f346a45cd0..79723e76af66 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/static_key.h>
 #include <linux/netfilter.h>
+#include <linux/locallock.h>
 #include <uapi/linux/netfilter/x_tables.h>
 
 /* Test a struct->invflags and a boolean for inequality */
@@ -341,6 +342,8 @@ void xt_free_table_info(struct xt_table_info *info);
  */
 DECLARE_PER_CPU(seqcount_t, xt_recseq);
 
+DECLARE_LOCAL_IRQ_LOCK(xt_write_lock);
+
 /* xt_tee_enabled - true if x_tables needs to handle reentrancy
  *
  * Enabled if current ip(6)tables ruleset has at least one -j TEE rule.
@@ -361,6 +364,9 @@ static inline unsigned int xt_write_recseq_begin(void)
 {
        unsigned int addend;
 
+       /* RT protection */
+       local_lock(xt_write_lock);
+
        /*
         * Low order bit of sequence is set if we already
         * called xt_write_recseq_begin().
@@ -391,6 +397,7 @@ static inline void xt_write_recseq_end(unsigned int addend)
        /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */
        smp_wmb();
        __this_cpu_add(xt_recseq.sequence, addend);
+       local_unlock(xt_write_lock);
 }
 
 /*
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f0015f801a78..c38288622819 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -162,7 +162,11 @@ struct nfs_inode {
 
        /* Readers: in-flight sillydelete RPC calls */
        /* Writers: rmdir */
+#ifdef CONFIG_PREEMPT_RT_BASE
+       struct semaphore        rmdir_sem;
+#else
        struct rw_semaphore     rmdir_sem;
+#endif
        struct mutex            commit_mutex;
 
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 6959968dc36a..802e849b57ac 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1530,7 +1530,7 @@ struct nfs_unlinkdata {
        struct nfs_removeargs args;
        struct nfs_removeres res;
        struct dentry *dentry;
-       wait_queue_head_t wq;
+       struct swait_queue_head wq;
        struct rpc_cred *cred;
        struct nfs_fattr dir_attr;
        long timeout;
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 6d731110e0db..e758627da14d 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -7,7 +7,7 @@
  *
  *                             Alan Cox <Alan.Cox@linux.org>
  */
- 
+
 #ifndef _LINUX_NOTIFIER_H
 #define _LINUX_NOTIFIER_H
 #include <linux/errno.h>
@@ -43,9 +43,7 @@
  * in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
  * As compensation, srcu_notifier_chain_unregister() is rather expensive.
  * SRCU notifier chains should be used when the chain will be called very
- * often but notifier_blocks will seldom be removed.  Also, SRCU notifier
- * chains are slightly more difficult to use because they require special
- * runtime initialization.
+ * often but notifier_blocks will seldom be removed.
  */
 
 struct notifier_block;
@@ -91,7 +89,7 @@ struct srcu_notifier_head {
                (name)->head = NULL;            \
        } while (0)
 
-/* srcu_notifier_heads must be initialized and cleaned up dynamically */
+/* srcu_notifier_heads must be cleaned up dynamically */
 extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 #define srcu_cleanup_notifier_head(name)       \
                cleanup_srcu_struct(&(name)->srcu);
@@ -104,7 +102,13 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
                .head = NULL }
 #define RAW_NOTIFIER_INIT(name)        {                               \
                .head = NULL }
-/* srcu_notifier_heads cannot be initialized statically */
+
+#define SRCU_NOTIFIER_INIT(name, pcpu)                         \
+       {                                                       \
+               .mutex = __MUTEX_INITIALIZER(name.mutex),       \
+               .head = NULL,                                   \
+               .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu),    \
+       }
 
 #define ATOMIC_NOTIFIER_HEAD(name)                             \
        struct atomic_notifier_head name =                      \
@@ -116,6 +120,26 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
        struct raw_notifier_head name =                         \
                RAW_NOTIFIER_INIT(name)
 
+#ifdef CONFIG_TREE_SRCU
+#define _SRCU_NOTIFIER_HEAD(name, mod)                         \
+       static DEFINE_PER_CPU(struct srcu_data,                 \
+                       name##_head_srcu_data);                 \
+       mod struct srcu_notifier_head name =                    \
+                       SRCU_NOTIFIER_INIT(name, name##_head_srcu_data)
+
+#else
+#define _SRCU_NOTIFIER_HEAD(name, mod)                         \
+       mod struct srcu_notifier_head name =                    \
+                       SRCU_NOTIFIER_INIT(name, name)
+
+#endif
+
+#define SRCU_NOTIFIER_HEAD(name)                               \
+       _SRCU_NOTIFIER_HEAD(name, )
+
+#define SRCU_NOTIFIER_HEAD_STATIC(name)                                \
+       _SRCU_NOTIFIER_HEAD(name, static)
+
 #ifdef __KERNEL__
 
 extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
@@ -185,12 +209,12 @@ static inline int notifier_to_errno(int ret)
 
 /*
  *     Declared notifiers so far. I can imagine quite a few more chains
- *     over time (eg laptop power reset chains, reboot chain (to clean 
+ *     over time (eg laptop power reset chains, reboot chain (to clean
  *     device units up), device [un]mount chain, module load/unload chain,
- *     low memory chain, screenblank chain (for plug in modular screenblankers) 
+ *     low memory chain, screenblank chain (for plug in modular screenblankers)
  *     VC switch chains (for loadable kernel svgalib VC switch helpers) etc...
  */
- 
+
 /* CPU notfiers are defined in include/linux/cpu.h. */
 
 /* netdevice notifiers are defined in include/linux/netdevice.h */
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 79b99d653e03..fb44e237316d 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -29,7 +29,7 @@ static struct percpu_rw_semaphore name = {                            \
 extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
 extern void __percpu_up_read(struct percpu_rw_semaphore *);
 
-static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem)
+static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 {
        might_sleep();
 
@@ -47,16 +47,10 @@ static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *
        __this_cpu_inc(*sem->read_count);
        if (unlikely(!rcu_sync_is_idle(&sem->rss)))
                __percpu_down_read(sem, false); /* Unconditional memory barrier */
-       barrier();
        /*
-        * The barrier() prevents the compiler from
+        * The preempt_enable() prevents the compiler from
         * bleeding the critical section out.
         */
-}
-
-static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
-{
-       percpu_down_read_preempt_disable(sem);
        preempt_enable();
 }
 
@@ -83,13 +77,9 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
        return ret;
 }
 
-static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem)
+static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 {
-       /*
-        * The barrier() prevents the compiler from
-        * bleeding the critical section out.
-        */
-       barrier();
+       preempt_disable();
        /*
         * Same as in percpu_down_read().
         */
@@ -102,12 +92,6 @@ static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem
        rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_);
 }
 
-static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
-{
-       preempt_disable();
-       percpu_up_read_preempt_enable(sem);
-}
-
 extern void percpu_down_write(struct percpu_rw_semaphore *);
 extern void percpu_up_write(struct percpu_rw_semaphore *);
 
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 296bbe49d5d1..4414796e3941 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -19,6 +19,35 @@
 #define PERCPU_MODULE_RESERVE          0
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+#define get_local_var(var) (*({        \
+       migrate_disable();      \
+       this_cpu_ptr(&var);     }))
+
+#define put_local_var(var) do {        \
+       (void)&(var);           \
+       migrate_enable();       \
+} while (0)
+
+# define get_local_ptr(var) ({ \
+       migrate_disable();      \
+       this_cpu_ptr(var);      })
+
+# define put_local_ptr(var) do {       \
+       (void)(var);                    \
+       migrate_enable();               \
+} while (0)
+
+#else
+
+#define get_local_var(var)     get_cpu_var(var)
+#define put_local_var(var)     put_cpu_var(var)
+#define get_local_ptr(var)     get_cpu_ptr(var)
+#define put_local_ptr(var)     put_cpu_ptr(var)
+
+#endif
+
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE             PFN_ALIGN(32 << 10)
 
diff --git a/include/linux/pid.h b/include/linux/pid.h
index dfd684ce0787..bc954a99aa70 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -3,6 +3,7 @@
 #define _LINUX_PID_H
 
 #include <linux/rculist.h>
+#include <linux/atomic.h>
 
 enum pid_type
 {
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 437a539898ae..de5c49b0dccf 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -101,8 +101,8 @@ struct k_itimer {
                struct {
                        struct alarm    alarmtimer;
                } alarm;
-               struct rcu_head         rcu;
        } it;
+       struct rcu_head         rcu;
 };
 
 void run_posix_cpu_timers(struct task_struct *task);
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 5bd3f151da78..6728662a81e8 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -51,7 +51,11 @@
 #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
 #define NMI_OFFSET     (1UL << NMI_SHIFT)
 
-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define SOFTIRQ_DISABLE_OFFSET                (2 * SOFTIRQ_OFFSET)
+#else
+# define SOFTIRQ_DISABLE_OFFSET                (0)
+#endif
 
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED   0x80000000
@@ -81,9 +85,15 @@
 #include <asm/preempt.h>
 
 #define hardirq_count()        (preempt_count() & HARDIRQ_MASK)
-#define softirq_count()        (preempt_count() & SOFTIRQ_MASK)
 #define irq_count()    (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
                                 | NMI_MASK))
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define softirq_count()       (preempt_count() & SOFTIRQ_MASK)
+# define in_serving_softirq()  (softirq_count() & SOFTIRQ_OFFSET)
+#else
+# define softirq_count()       (0UL)
+extern int in_serving_softirq(void);
+#endif
 
 /*
  * Are we doing bottom half or hardware interrupt processing?
@@ -101,7 +111,6 @@
 #define in_irq()               (hardirq_count())
 #define in_softirq()           (softirq_count())
 #define in_interrupt()         (irq_count())
-#define in_serving_softirq()   (softirq_count() & SOFTIRQ_OFFSET)
 #define in_nmi()               (preempt_count() & NMI_MASK)
 #define in_task()              (!(preempt_count() & \
                                   (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
@@ -118,7 +127,11 @@
 /*
  * The preempt_count offset after spin_lock()
  */
+#if !defined(CONFIG_PREEMPT_RT_FULL)
 #define PREEMPT_LOCK_OFFSET    PREEMPT_DISABLE_OFFSET
+#else
+#define PREEMPT_LOCK_OFFSET    0
+#endif
 
 /*
  * The preempt_count offset needed for things like:
@@ -167,6 +180,20 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#ifdef CONFIG_PREEMPT_LAZY
+#define add_preempt_lazy_count(val)    do { preempt_lazy_count() += (val); } while (0)
+#define sub_preempt_lazy_count(val)    do { preempt_lazy_count() -= (val); } while (0)
+#define inc_preempt_lazy_count()       add_preempt_lazy_count(1)
+#define dec_preempt_lazy_count()       sub_preempt_lazy_count(1)
+#define preempt_lazy_count()           (current_thread_info()->preempt_lazy_count)
+#else
+#define add_preempt_lazy_count(val)    do { } while (0)
+#define sub_preempt_lazy_count(val)    do { } while (0)
+#define inc_preempt_lazy_count()       do { } while (0)
+#define dec_preempt_lazy_count()       do { } while (0)
+#define preempt_lazy_count()           (0)
+#endif
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
@@ -175,16 +202,53 @@ do { \
        barrier(); \
 } while (0)
 
+#define preempt_lazy_disable() \
+do { \
+       inc_preempt_lazy_count(); \
+       barrier(); \
+} while (0)
+
 #define sched_preempt_enable_no_resched() \
 do { \
        barrier(); \
        preempt_count_dec(); \
 } while (0)
 
-#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+# define preempt_check_resched_rt() preempt_check_resched()
+#else
+# define preempt_enable_no_resched() preempt_enable()
+# define preempt_check_resched_rt() barrier();
+#endif
 
 #define preemptible()  (preempt_count() == 0 && !irqs_disabled())
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+
+int __migrate_disabled(struct task_struct *p);
+
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+static inline int __migrate_disabled(struct task_struct *p)
+{
+       return 0;
+}
+
+#else
+#define migrate_disable()              preempt_disable()
+#define migrate_enable()               preempt_enable()
+static inline int __migrate_disabled(struct task_struct *p)
+{
+       return 0;
+}
+#endif
+
 #ifdef CONFIG_PREEMPT
 #define preempt_enable() \
 do { \
@@ -206,6 +270,13 @@ do { \
                __preempt_schedule(); \
 } while (0)
 
+#define preempt_lazy_enable() \
+do { \
+       dec_preempt_lazy_count(); \
+       barrier(); \
+       preempt_check_resched(); \
+} while (0)
+
 #else /* !CONFIG_PREEMPT */
 #define preempt_enable() \
 do { \
@@ -213,6 +284,12 @@ do { \
        preempt_count_dec(); \
 } while (0)
 
+#define preempt_lazy_enable() \
+do { \
+       dec_preempt_lazy_count(); \
+       barrier(); \
+} while (0)
+
 #define preempt_enable_notrace() \
 do { \
        barrier(); \
@@ -251,8 +328,16 @@ do { \
 #define preempt_disable_notrace()              barrier()
 #define preempt_enable_no_resched_notrace()    barrier()
 #define preempt_enable_notrace()               barrier()
+#define preempt_check_resched_rt()             barrier()
 #define preemptible()                          0
 
+#define migrate_disable()                      barrier()
+#define migrate_enable()                       barrier()
+
+static inline int __migrate_disabled(struct task_struct *p)
+{
+       return 0;
+}
 #endif /* CONFIG_PREEMPT_COUNT */
 
 #ifdef MODULE
@@ -271,10 +356,22 @@ do { \
 } while (0)
 #define preempt_fold_need_resched() \
 do { \
-       if (tif_need_resched()) \
+       if (tif_need_resched_now()) \
                set_preempt_need_resched(); \
 } while (0)
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define preempt_disable_rt()          preempt_disable()
+# define preempt_enable_rt()           preempt_enable()
+# define preempt_disable_nort()                barrier()
+# define preempt_enable_nort()         barrier()
+#else
+# define preempt_disable_rt()          barrier()
+# define preempt_enable_rt()           barrier()
+# define preempt_disable_nort()                preempt_disable()
+# define preempt_enable_nort()         preempt_enable()
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 6106befed756..1dba9cb7b91b 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -142,9 +142,11 @@ struct va_format {
 #ifdef CONFIG_EARLY_PRINTK
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
+extern void printk_kill(void);
 #else
 static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
+static inline void printk_kill(void) { }
 #endif
 
 #ifdef CONFIG_PRINTK_NMI
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 567ebb5eaab0..9da7ea957399 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -328,6 +328,8 @@ unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *,
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order);
+void radix_tree_preload_end(void);
+
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *,
                        unsigned long index, unsigned int tag);
@@ -347,11 +349,6 @@ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *,
                unsigned int max_items, unsigned int tag);
 int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag);
 
-static inline void radix_tree_preload_end(void)
-{
-       preempt_enable();
-}
-
 int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t);
 int radix_tree_split(struct radix_tree_root *, unsigned long index,
                        unsigned new_order);
diff --git a/include/linux/random.h b/include/linux/random.h
index 4024f7d9c77d..462d752a739b 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -32,7 +32,7 @@ static inline void add_latent_entropy(void) {}
 
 extern void add_input_randomness(unsigned int type, unsigned int code,
                                 unsigned int value) __latent_entropy;
-extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
+extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) __latent_entropy;
 
 extern void get_random_bytes(void *buf, int nbytes);
 extern int wait_for_random_bytes(void);
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index d574361943ea..0a9f442409b9 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -31,7 +31,7 @@
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
-#include <linux/rcupdate.h>
+#include <linux/rcu_assign_pointer.h>
 
 struct rb_node {
        unsigned long  __rb_parent_color;
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 6bfd2b581f75..af8a61be2d8d 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -26,6 +26,7 @@
 
 #include <linux/compiler.h>
 #include <linux/rbtree.h>
+#include <linux/rcupdate.h>
 
 /*
  * Please note - only struct rb_augment_callbacks and the prototypes for
diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index ece43e882b56..7d012faa509a 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -35,6 +35,7 @@
 
 #include <linux/rbtree.h>
 #include <linux/seqlock.h>
+#include <linux/rcupdate.h>
 
 struct latch_tree_node {
        struct rb_node node[2];
diff --git a/include/linux/rcu_assign_pointer.h b/include/linux/rcu_assign_pointer.h
new file mode 100644
index 000000000000..7066962a4379
--- /dev/null
+++ b/include/linux/rcu_assign_pointer.h
@@ -0,0 +1,54 @@
+#ifndef __LINUX_RCU_ASSIGN_POINTER_H__
+#define __LINUX_RCU_ASSIGN_POINTER_H__
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/**
+ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
+ * @v: The value to statically initialize with.
+ */
+#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
+
+/**
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
+ *
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.
+ *
+ * Inserts memory barriers on architectures that require them
+ * (which is most of them), and also prevents the compiler from
+ * reordering the code that initializes the structure after the pointer
+ * assignment.  More importantly, this call documents which pointers
+ * will be dereferenced by RCU read-side code.
+ *
+ * In some special cases, you may use RCU_INIT_POINTER() instead
+ * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
+ * to the fact that it does not constrain either the CPU or the compiler.
+ * That said, using RCU_INIT_POINTER() when you should have used
+ * rcu_assign_pointer() is a very bad thing that results in
+ * impossible-to-diagnose memory corruption.  So please be careful.
+ * See the RCU_INIT_POINTER() comment header for details.
+ *
+ * Note that rcu_assign_pointer() evaluates each of its arguments only
+ * once, appearances notwithstanding.  One of the "extra" evaluations
+ * is in typeof() and the other visible only to sparse (__CHECKER__),
+ * neither of which actually execute the argument.  As with most cpp
+ * macros, this execute-arguments-only-once property is important, so
+ * please be careful when making changes to rcu_assign_pointer() and the
+ * other macros that it invokes.
+ */
+#define rcu_assign_pointer(p, v)                                             \
+({                                                                           \
+       uintptr_t _r_a_p__v = (uintptr_t)(v);                                 \
+                                                                             \
+       if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)        \
+               WRITE_ONCE((p), (typeof(p))(_r_a_p__v));                      \
+       else                                                                  \
+               smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
+       _r_a_p__v;                                                            \
+})
+
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a6ddc42f87a5..70996e134818 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -42,6 +42,7 @@
 #include <linux/lockdep.h>
 #include <asm/processor.h>
 #include <linux/cpumask.h>
+#include <linux/rcu_assign_pointer.h>
 
 #define ULONG_CMP_GE(a, b)     (ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)     (ULONG_MAX / 2 < (a) - (b))
@@ -55,7 +56,11 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 #define        call_rcu        call_rcu_sched
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define call_rcu_bh    call_rcu
+#else
 void call_rcu_bh(struct rcu_head *head, rcu_callback_t func);
+#endif
 void call_rcu_sched(struct rcu_head *head, rcu_callback_t func);
 void synchronize_sched(void);
 void rcu_barrier_tasks(void);
@@ -74,6 +79,11 @@ void synchronize_rcu(void);
  * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
  */
 #define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+#ifndef CONFIG_PREEMPT_RT_FULL
+#define sched_rcu_preempt_depth()      rcu_preempt_depth()
+#else
+static inline int sched_rcu_preempt_depth(void) { return 0; }
+#endif
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
@@ -99,6 +109,8 @@ static inline int rcu_preempt_depth(void)
        return 0;
 }
 
+#define sched_rcu_preempt_depth()      rcu_preempt_depth()
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /* Internal to kernel */
@@ -255,7 +267,14 @@ extern struct lockdep_map rcu_sched_lock_map;
 extern struct lockdep_map rcu_callback_map;
 int debug_lockdep_rcu_enabled(void);
 int rcu_read_lock_held(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int rcu_read_lock_bh_held(void)
+{
+       return rcu_read_lock_held();
+}
+#else
 int rcu_read_lock_bh_held(void);
+#endif
 int rcu_read_lock_sched_held(void);
 
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
@@ -364,54 +383,6 @@ static inline void rcu_preempt_sleep_check(void) { }
        ((typeof(*p) __force __kernel *)(________p1)); \
 })
 
-/**
- * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
- * @v: The value to statically initialize with.
- */
-#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
-
-/**
- * rcu_assign_pointer() - assign to RCU-protected pointer
- * @p: pointer to assign to
- * @v: value to assign (publish)
- *
- * Assigns the specified value to the specified RCU-protected
- * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.
- *
- * Inserts memory barriers on architectures that require them
- * (which is most of them), and also prevents the compiler from
- * reordering the code that initializes the structure after the pointer
- * assignment.  More importantly, this call documents which pointers
- * will be dereferenced by RCU read-side code.
- *
- * In some special cases, you may use RCU_INIT_POINTER() instead
- * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
- * to the fact that it does not constrain either the CPU or the compiler.
- * That said, using RCU_INIT_POINTER() when you should have used
- * rcu_assign_pointer() is a very bad thing that results in
- * impossible-to-diagnose memory corruption.  So please be careful.
- * See the RCU_INIT_POINTER() comment header for details.
- *
- * Note that rcu_assign_pointer() evaluates each of its arguments only
- * once, appearances notwithstanding.  One of the "extra" evaluations
- * is in typeof() and the other visible only to sparse (__CHECKER__),
- * neither of which actually execute the argument.  As with most cpp
- * macros, this execute-arguments-only-once property is important, so
- * please be careful when making changes to rcu_assign_pointer() and the
- * other macros that it invokes.
- */
-#define rcu_assign_pointer(p, v)                                             \
-({                                                                           \
-       uintptr_t _r_a_p__v = (uintptr_t)(v);                                 \
-                                                                             \
-       if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)        \
-               WRITE_ONCE((p), (typeof(p))(_r_a_p__v));                      \
-       else                                                                  \
-               smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
-       _r_a_p__v;                                                            \
-})
-
 /**
  * rcu_swap_protected() - swap an RCU and a regular pointer
  * @rcu_ptr: RCU pointer
@@ -707,10 +678,14 @@ static inline void rcu_read_unlock(void)
 static inline void rcu_read_lock_bh(void)
 {
        local_bh_disable();
+#ifdef CONFIG_PREEMPT_RT_FULL
+       rcu_read_lock();
+#else
        __acquire(RCU_BH);
        rcu_lock_acquire(&rcu_bh_lock_map);
        RCU_LOCKDEP_WARN(!rcu_is_watching(),
                         "rcu_read_lock_bh() used illegally while idle");
+#endif
 }
 
 /*
@@ -720,10 +695,14 @@ static inline void rcu_read_lock_bh(void)
  */
 static inline void rcu_read_unlock_bh(void)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       rcu_read_unlock();
+#else
        RCU_LOCKDEP_WARN(!rcu_is_watching(),
                         "rcu_read_unlock_bh() used illegally while idle");
        rcu_lock_release(&rcu_bh_lock_map);
        __release(RCU_BH);
+#endif
        local_bh_enable();
 }
 
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 37d6fd3b7ff8..a082fde7d6bc 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -44,7 +44,11 @@ static inline void rcu_virt_note_context_switch(int cpu)
        rcu_note_context_switch(false);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define synchronize_rcu_bh    synchronize_rcu
+#else
 void synchronize_rcu_bh(void);
+#endif
 void synchronize_sched_expedited(void);
 void synchronize_rcu_expedited(void);
 
@@ -72,7 +76,11 @@ static inline void synchronize_rcu_bh_expedited(void)
 }
 
 void rcu_barrier(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define rcu_barrier_bh                rcu_barrier
+#else
 void rcu_barrier_bh(void);
+#endif
 void rcu_barrier_sched(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 5caa062a02b2..abce5f5325e1 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -34,10 +34,12 @@ struct ring_buffer_event {
  *                              array[0] = time delta (28 .. 59)
  *                              size = 8 bytes
  *
- * @RINGBUF_TYPE_TIME_STAMP:   Sync time stamp with external clock
- *                              array[0]    = tv_nsec
- *                              array[1..2] = tv_sec
- *                              size = 16 bytes
+ * @RINGBUF_TYPE_TIME_STAMP:   Absolute timestamp
+ *                              Same format as TIME_EXTEND except that the
+ *                              value is an absolute timestamp, not a delta
+ *                              event.time_delta contains bottom 27 bits
+ *                              array[0] = top (28 .. 59) bits
+ *                              size = 8 bytes
  *
  * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
  *                             Data record
@@ -54,12 +56,12 @@ enum ring_buffer_type {
        RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
        RINGBUF_TYPE_PADDING,
        RINGBUF_TYPE_TIME_EXTEND,
-       /* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
        RINGBUF_TYPE_TIME_STAMP,
 };
 
 unsigned ring_buffer_event_length(struct ring_buffer_event *event);
 void *ring_buffer_event_data(struct ring_buffer_event *event);
+u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event);
 
 /*
  * ring_buffer_discard_commit will remove an event that has not
@@ -115,6 +117,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 int ring_buffer_write(struct ring_buffer *buffer,
                      unsigned long length, void *data);
 
+void ring_buffer_nest_start(struct ring_buffer *buffer);
+void ring_buffer_nest_end(struct ring_buffer *buffer);
+
 struct ring_buffer_event *
 ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
                 unsigned long *lost_events);
@@ -179,6 +184,8 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
                                      int cpu, u64 *ts);
 void ring_buffer_set_clock(struct ring_buffer *buffer,
                           u64 (*clock)(void));
+void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs);
+bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer);
 
 size_t ring_buffer_page_len(void *page);
 
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 6fd615a0eea9..138bd1e183e0 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -14,11 +14,15 @@
 #define __LINUX_RT_MUTEX_H
 
 #include <linux/linkage.h>
+#include <linux/spinlock_types_raw.h>
 #include <linux/rbtree.h>
-#include <linux/spinlock_types.h>
 
 extern int max_lock_depth; /* for sysctl */
 
+#ifdef CONFIG_DEBUG_MUTEXES
+#include <linux/debug_locks.h>
+#endif
+
 /**
  * The rt_mutex structure
  *
@@ -31,8 +35,8 @@ struct rt_mutex {
        raw_spinlock_t          wait_lock;
        struct rb_root_cached   waiters;
        struct task_struct      *owner;
-#ifdef CONFIG_DEBUG_RT_MUTEXES
        int                     save_state;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
        const char              *name, *file;
        int                     line;
        void                    *magic;
@@ -82,16 +86,23 @@ do { \
 #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)
 #endif
 
-#define __RT_MUTEX_INITIALIZER(mutexname) \
-       { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
+#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
+       .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
        , .waiters = RB_ROOT_CACHED \
        , .owner = NULL \
        __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
-       __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)}
+       __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)
+
+#define __RT_MUTEX_INITIALIZER(mutexname) \
+       { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) }
 
 #define DEFINE_RT_MUTEX(mutexname) \
        struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
 
+#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \
+       { __RT_MUTEX_INITIALIZER_PLAIN(mutexname)    \
+               , .save_state = 1 }
+
 /**
  * rt_mutex_is_locked - is the mutex locked
  * @lock: the mutex to be queried
@@ -115,6 +126,7 @@ extern void rt_mutex_lock(struct rt_mutex *lock);
 #endif
 
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
                               struct hrtimer_sleeper *timeout);
 
diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h
new file mode 100644
index 000000000000..a9c4c2ac4d1f
--- /dev/null
+++ b/include/linux/rwlock_rt.h
@@ -0,0 +1,119 @@
+#ifndef __LINUX_RWLOCK_RT_H
+#define __LINUX_RWLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+extern void __lockfunc rt_write_lock(rwlock_t *rwlock);
+extern void __lockfunc rt_read_lock(rwlock_t *rwlock);
+extern int __lockfunc rt_write_trylock(rwlock_t *rwlock);
+extern int __lockfunc rt_read_trylock(rwlock_t *rwlock);
+extern void __lockfunc rt_write_unlock(rwlock_t *rwlock);
+extern void __lockfunc rt_read_unlock(rwlock_t *rwlock);
+extern int __lockfunc rt_read_can_lock(rwlock_t *rwlock);
+extern int __lockfunc rt_write_can_lock(rwlock_t *rwlock);
+extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key);
+
+#define read_can_lock(rwlock)          rt_read_can_lock(rwlock)
+#define write_can_lock(rwlock)         rt_write_can_lock(rwlock)
+
+#define read_trylock(lock)     __cond_lock(lock, rt_read_trylock(lock))
+#define write_trylock(lock)    __cond_lock(lock, rt_write_trylock(lock))
+
+static inline int __write_trylock_rt_irqsave(rwlock_t *lock, unsigned long *flags)
+{
+       /* XXX ARCH_IRQ_ENABLED */
+       *flags = 0;
+       return rt_write_trylock(lock);
+}
+
+#define write_trylock_irqsave(lock, flags)             \
+       __cond_lock(lock, __write_trylock_rt_irqsave(lock, &(flags)))
+
+#define read_lock_irqsave(lock, flags)                 \
+       do {                                            \
+               typecheck(unsigned long, flags);        \
+               rt_read_lock(lock);                     \
+               flags = 0;                              \
+       } while (0)
+
+#define write_lock_irqsave(lock, flags)                        \
+       do {                                            \
+               typecheck(unsigned long, flags);        \
+               rt_write_lock(lock);                    \
+               flags = 0;                              \
+       } while (0)
+
+#define read_lock(lock)                rt_read_lock(lock)
+
+#define read_lock_bh(lock)                             \
+       do {                                            \
+               local_bh_disable();                     \
+               rt_read_lock(lock);                     \
+       } while (0)
+
+#define read_lock_irq(lock)    read_lock(lock)
+
+#define write_lock(lock)       rt_write_lock(lock)
+
+#define write_lock_bh(lock)                            \
+       do {                                            \
+               local_bh_disable();                     \
+               rt_write_lock(lock);                    \
+       } while (0)
+
+#define write_lock_irq(lock)   write_lock(lock)
+
+#define read_unlock(lock)      rt_read_unlock(lock)
+
+#define read_unlock_bh(lock)                           \
+       do {                                            \
+               rt_read_unlock(lock);                   \
+               local_bh_enable();                      \
+       } while (0)
+
+#define read_unlock_irq(lock)  read_unlock(lock)
+
+#define write_unlock(lock)     rt_write_unlock(lock)
+
+#define write_unlock_bh(lock)                          \
+       do {                                            \
+               rt_write_unlock(lock);                  \
+               local_bh_enable();                      \
+       } while (0)
+
+#define write_unlock_irq(lock) write_unlock(lock)
+
+#define read_unlock_irqrestore(lock, flags)            \
+       do {                                            \
+               typecheck(unsigned long, flags);        \
+               (void) flags;                           \
+               rt_read_unlock(lock);                   \
+       } while (0)
+
+#define write_unlock_irqrestore(lock, flags) \
+       do {                                            \
+               typecheck(unsigned long, flags);        \
+               (void) flags;                           \
+               rt_write_unlock(lock);                  \
+       } while (0)
+
+#define rwlock_init(rwl)                               \
+do {                                                   \
+       static struct lock_class_key __key;             \
+                                                       \
+       __rt_rwlock_init(rwl, #rwl, &__key);            \
+} while (0)
+
+/*
+ * Internal functions made global for CPU pinning
+ */
+void __read_rt_lock(struct rt_rw_lock *lock);
+int __read_rt_trylock(struct rt_rw_lock *lock);
+void __write_rt_lock(struct rt_rw_lock *lock);
+int __write_rt_trylock(struct rt_rw_lock *lock);
+void __read_rt_unlock(struct rt_rw_lock *lock);
+void __write_rt_unlock(struct rt_rw_lock *lock);
+
+#endif
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index cc0072e93e36..5317cd957292 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -1,6 +1,10 @@
 #ifndef __LINUX_RWLOCK_TYPES_H
 #define __LINUX_RWLOCK_TYPES_H
 
+#if !defined(__LINUX_SPINLOCK_TYPES_H)
+# error "Do not include directly, include spinlock_types.h"
+#endif
+
 /*
  * include/linux/rwlock_types.h - generic rwlock type definitions
  *                               and initializers
diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h
new file mode 100644
index 000000000000..546a1f8f1274
--- /dev/null
+++ b/include/linux/rwlock_types_rt.h
@@ -0,0 +1,55 @@
+#ifndef __LINUX_RWLOCK_TYPES_RT_H
+#define __LINUX_RWLOCK_TYPES_RT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define RW_DEP_MAP_INIT(lockname)     .dep_map = { .name = #lockname }
+#else
+# define RW_DEP_MAP_INIT(lockname)
+#endif
+
+typedef struct rt_rw_lock rwlock_t;
+
+#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name)
+
+#define DEFINE_RWLOCK(name) \
+       rwlock_t name = __RW_LOCK_UNLOCKED(name)
+
+/*
+ * A reader biased implementation primarily for CPU pinning.
+ *
+ * Can be selected as general replacement for the single reader RT rwlock
+ * variant
+ */
+struct rt_rw_lock {
+       struct rt_mutex         rtmutex;
+       atomic_t                readers;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       struct lockdep_map      dep_map;
+#endif
+};
+
+#define READER_BIAS    (1U << 31)
+#define WRITER_BIAS    (1U << 30)
+
+#define __RWLOCK_RT_INITIALIZER(name)                                  \
+{                                                                      \
+       .readers = ATOMIC_INIT(READER_BIAS),                            \
+       .rtmutex = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.rtmutex),     \
+       RW_DEP_MAP_INIT(name)                                           \
+}
+
+void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name,
+                            struct lock_class_key *key);
+
+#define rwlock_biased_rt_init(rwlock)                                  \
+       do {                                                            \
+               static struct lock_class_key __key;                     \
+                                                                       \
+               __rwlock_biased_rt_init((rwlock), #rwlock, &__key);     \
+       } while (0)
+
+#endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index c427ffaa4904..513df11a364e 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -20,6 +20,10 @@
 #include <linux/osq_lock.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#include <linux/rwsem_rt.h>
+#else /* PREEMPT_RT_FULL */
+
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -114,6 +118,13 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
        return !list_empty(&sem->wait_list);
 }
 
+#endif /* !PREEMPT_RT_FULL */
+
+/*
+ * The functions below are the same for all rwsem implementations including
+ * the RT specific variant.
+ */
+
 /*
  * lock for reading
  */
diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h
new file mode 100644
index 000000000000..2ffbf093ae92
--- /dev/null
+++ b/include/linux/rwsem_rt.h
@@ -0,0 +1,67 @@
+#ifndef _LINUX_RWSEM_RT_H
+#define _LINUX_RWSEM_RT_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Include rwsem.h"
+#endif
+
+#include <linux/rtmutex.h>
+#include <linux/swait.h>
+
+#define READER_BIAS            (1U << 31)
+#define WRITER_BIAS            (1U << 30)
+
+struct rw_semaphore {
+       atomic_t                readers;
+       struct rt_mutex         rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       struct lockdep_map      dep_map;
+#endif
+};
+
+#define __RWSEM_INITIALIZER(name)                              \
+{                                                              \
+       .readers = ATOMIC_INIT(READER_BIAS),                    \
+       .rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex),        \
+       RW_DEP_MAP_INIT(name)                                   \
+}
+
+#define DECLARE_RWSEM(lockname) \
+       struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
+
+extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+                         struct lock_class_key *key);
+
+#define __init_rwsem(sem, name, key)                   \
+do {                                                   \
+               rt_mutex_init(&(sem)->rtmutex);         \
+               __rwsem_init((sem), (name), (key));     \
+} while (0)
+
+#define init_rwsem(sem)                                        \
+do {                                                   \
+       static struct lock_class_key __key;             \
+                                                       \
+       __init_rwsem((sem), #sem, &__key);              \
+} while (0)
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+       return atomic_read(&sem->readers) != READER_BIAS;
+}
+
+static inline int rwsem_is_contended(struct rw_semaphore *sem)
+{
+       return atomic_read(&sem->readers) > 0;
+}
+
+extern void __down_read(struct rw_semaphore *sem);
+extern int __down_read_trylock(struct rw_semaphore *sem);
+extern void __down_write(struct rw_semaphore *sem);
+extern int __must_check __down_write_killable(struct rw_semaphore *sem);
+extern int __down_write_trylock(struct rw_semaphore *sem);
+extern void __up_read(struct rw_semaphore *sem);
+extern void __up_write(struct rw_semaphore *sem);
+extern void __downgrade_write(struct rw_semaphore *sem);
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e04919aa8201..a6ffb552be01 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -27,6 +27,7 @@
 #include <linux/signal_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
+#include <asm/kmap_types.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -93,7 +94,6 @@ struct task_group;
 
 /* Convenience macros for the sake of wake_up(): */
 #define TASK_NORMAL                    (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
-#define TASK_ALL                       (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
 
 /* get_task_state(): */
 #define TASK_REPORT                    (TASK_RUNNING | TASK_INTERRUPTIBLE | \
@@ -101,12 +101,8 @@ struct task_group;
                                         __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
                                         TASK_PARKED)
 
-#define task_is_traced(task)           ((task->state & __TASK_TRACED) != 0)
-
 #define task_is_stopped(task)          ((task->state & __TASK_STOPPED) != 0)
 
-#define task_is_stopped_or_traced(task)        ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
-
 #define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
                                         (task->flags & PF_FROZEN) == 0 && \
                                         (task->state & TASK_NOLOAD) == 0)
@@ -134,6 +130,11 @@ struct task_group;
                smp_store_mb(current->state, (state_value));    \
        } while (0)
 
+#define __set_current_state_no_track(state_value)              \
+               current->state = (state_value);
+#define set_current_state_no_track(state_value)                        \
+               smp_store_mb(current->state, (state_value));
+
 #define set_special_state(state_value)                                 \
        do {                                                            \
                unsigned long flags; /* may shadow */                   \
@@ -187,6 +188,9 @@ struct task_group;
 #define set_current_state(state_value)                                 \
        smp_store_mb(current->state, (state_value))
 
+#define __set_current_state_no_track(state_value)      __set_current_state(state_value)
+#define set_current_state_no_track(state_value)                set_current_state(state_value)
+
 /*
  * set_special_state() should be used for those states when the blocking task
  * can not use the regular condition based wait-loop. In that case we must
@@ -566,6 +570,8 @@ struct task_struct {
 #endif
        /* -1 unrunnable, 0 runnable, >0 stopped: */
        volatile long                   state;
+       /* saved state for "spinlock sleepers" */
+       volatile long                   saved_state;
 
        /*
         * This begins the randomizable portion of task_struct. Only
@@ -618,7 +624,25 @@ struct task_struct {
 
        unsigned int                    policy;
        int                             nr_cpus_allowed;
-       cpumask_t                       cpus_allowed;
+       const cpumask_t                 *cpus_ptr;
+       cpumask_t                       cpus_mask;
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+       int                             migrate_disable;
+       int                             migrate_disable_update;
+       int                             pinned_on_cpu;
+# ifdef CONFIG_SCHED_DEBUG
+       int                             migrate_disable_atomic;
+# endif
+
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+# ifdef CONFIG_SCHED_DEBUG
+       int                             migrate_disable;
+       int                             migrate_disable_atomic;
+# endif
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+       int                             sleeping_lock;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
        int                             rcu_read_lock_nesting;
@@ -777,6 +801,9 @@ struct task_struct {
 #ifdef CONFIG_POSIX_TIMERS
        struct task_cputime             cputime_expires;
        struct list_head                cpu_timers[3];
+#ifdef CONFIG_PREEMPT_RT_BASE
+       struct task_struct              *posix_timer_list;
+#endif
 #endif
 
        /* Process credentials: */
@@ -820,11 +847,17 @@ struct task_struct {
        /* Signal handlers: */
        struct signal_struct            *signal;
        struct sighand_struct           *sighand;
+       struct sigqueue                 *sigqueue_cache;
+
        sigset_t                        blocked;
        sigset_t                        real_blocked;
        /* Restored if set_restore_sigmask() was used: */
        sigset_t                        saved_sigmask;
        struct sigpending               pending;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       /* TODO: move me into ->restart_block ? */
+       struct                          siginfo forced_info;
+#endif
        unsigned long                   sas_ss_sp;
        size_t                          sas_ss_size;
        unsigned int                    sas_ss_flags;
@@ -849,6 +882,7 @@ struct task_struct {
        raw_spinlock_t                  pi_lock;
 
        struct wake_q_node              wake_q;
+       struct wake_q_node              wake_q_sleeper;
 
 #ifdef CONFIG_RT_MUTEXES
        /* PI waiters blocked on a rt_mutex held by this task: */
@@ -1116,8 +1150,22 @@ struct task_struct {
        unsigned int                    sequential_io;
        unsigned int                    sequential_io_avg;
 #endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+       struct rcu_head                 put_rcu;
+       int                             softirq_nestcnt;
+       unsigned int                    softirqs_raised;
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32
+       int                             kmap_idx;
+       pte_t                           kmap_pte[KM_TYPE_NR];
+# endif
+#endif
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
        unsigned long                   task_state_change;
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+       int                             xmit_recursion;
 #endif
        int                             pagefault_disabled;
 #ifdef CONFIG_MMU
@@ -1332,6 +1380,7 @@ extern struct pid *cad_pid;
 /*
  * Per process flags
  */
+#define PF_IN_SOFTIRQ          0x00000001      /* Task is serving softirq */
 #define PF_IDLE                        0x00000002      /* I am an IDLE thread */
 #define PF_EXITING             0x00000004      /* Getting shut down */
 #define PF_EXITPIDONE          0x00000008      /* PI exit done on shut down */
@@ -1355,7 +1404,7 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD             0x00200000      /* I am a kernel thread */
 #define PF_RANDOMIZE           0x00400000      /* Randomize virtual address space */
 #define PF_SWAPWRITE           0x00800000      /* Allowed to write to swap */
-#define PF_NO_SETAFFINITY      0x04000000      /* Userland is not allowed to meddle with cpus_allowed */
+#define PF_NO_SETAFFINITY      0x04000000      /* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY           0x08000000      /* Early kill for mce process policy */
 #define PF_MUTEX_TESTER                0x20000000      /* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP                0x40000000      /* Freezer should not count it as freezable */
@@ -1535,6 +1584,7 @@ extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *n
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
+extern int wake_up_lock_sleeper(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
@@ -1611,6 +1661,89 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
        return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+static inline void set_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+       set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+       clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int test_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+       return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY));
+}
+
+static inline int need_resched_lazy(void)
+{
+       return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int need_resched_now(void)
+{
+       return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#else
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { }
+static inline int need_resched_lazy(void) { return 0; }
+
+static inline int need_resched_now(void)
+{
+       return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#endif
+
+
+static inline bool __task_is_stopped_or_traced(struct task_struct *task)
+{
+       if (task->state & (__TASK_STOPPED | __TASK_TRACED))
+               return true;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED))
+               return true;
+#endif
+       return false;
+}
+
+static inline bool task_is_stopped_or_traced(struct task_struct *task)
+{
+       bool traced_stopped;
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+       unsigned long flags;
+
+       raw_spin_lock_irqsave(&task->pi_lock, flags);
+       traced_stopped = __task_is_stopped_or_traced(task);
+       raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+#else
+       traced_stopped = __task_is_stopped_or_traced(task);
+#endif
+       return traced_stopped;
+}
+
+static inline bool task_is_traced(struct task_struct *task)
+{
+       bool traced = false;
+
+       if (task->state & __TASK_TRACED)
+               return true;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       /* in case the task is sleeping on tasklist_lock */
+       raw_spin_lock_irq(&task->pi_lock);
+       if (task->state & __TASK_TRACED)
+               traced = true;
+       else if (task->saved_state & __TASK_TRACED)
+               traced = true;
+       raw_spin_unlock_irq(&task->pi_lock);
+#endif
+       return traced;
+}
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
@@ -1636,12 +1769,16 @@ extern int __cond_resched_lock(spinlock_t *lock);
        __cond_resched_lock(lock);                              \
 })
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern int __cond_resched_softirq(void);
 
 #define cond_resched_softirq() ({                                      \
        ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);     \
        __cond_resched_softirq();                                       \
 })
+#else
+# define cond_resched_softirq()                cond_resched()
+#endif
 
 static inline void cond_resched_rcu(void)
 {
@@ -1671,6 +1808,23 @@ static __always_inline bool need_resched(void)
        return unlikely(tif_need_resched());
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline void sleeping_lock_inc(void)
+{
+       current->sleeping_lock++;
+}
+
+static inline void sleeping_lock_dec(void)
+{
+       current->sleeping_lock--;
+}
+
+#else
+
+static inline void sleeping_lock_inc(void) { }
+static inline void sleeping_lock_dec(void) { }
+#endif
+
 /*
  * Wrappers for p->thread_info->cpu access. No-op on UP.
  */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3d49b91b674d..d8f2fa8f500c 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -43,6 +43,17 @@ static inline void mmdrop(struct mm_struct *mm)
                __mmdrop(mm);
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+extern void __mmdrop_delayed(struct rcu_head *rhp);
+static inline void mmdrop_delayed(struct mm_struct *mm)
+{
+       if (atomic_dec_and_test(&mm->mm_count))
+               call_rcu(&mm->delayed_drop, __mmdrop_delayed);
+}
+#else
+# define mmdrop_delayed(mm)    mmdrop(mm)
+#endif
+
 static inline void mmdrop_async_fn(struct work_struct *work)
 {
        struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a74ec619ac51..8e7f741370c5 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -88,6 +88,15 @@ extern void sched_exec(void);
 
 #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+extern void __put_task_struct_cb(struct rcu_head *rhp);
+
+static inline void put_task_struct(struct task_struct *t)
+{
+       if (atomic_dec_and_test(&t->usage))
+               call_rcu(&t->put_rcu, __put_task_struct_cb);
+}
+#else
 extern void __put_task_struct(struct task_struct *t);
 
 static inline void put_task_struct(struct task_struct *t)
@@ -95,7 +104,7 @@ static inline void put_task_struct(struct task_struct *t)
        if (atomic_dec_and_test(&t->usage))
                __put_task_struct(t);
 }
-
+#endif
 struct task_struct *task_rcu_dereference(struct task_struct **ptask);
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 10b19a192b2d..ce3ccff3d9d8 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -47,8 +47,29 @@ static inline void wake_q_init(struct wake_q_head *head)
        head->lastp = &head->first;
 }
 
-extern void wake_q_add(struct wake_q_head *head,
-                      struct task_struct *task);
-extern void wake_up_q(struct wake_q_head *head);
+extern void __wake_q_add(struct wake_q_head *head,
+                        struct task_struct *task, bool sleeper);
+static inline void wake_q_add(struct wake_q_head *head,
+                             struct task_struct *task)
+{
+       __wake_q_add(head, task, false);
+}
+
+static inline void wake_q_add_sleeper(struct wake_q_head *head,
+                                     struct task_struct *task)
+{
+       __wake_q_add(head, task, true);
+}
+
+extern void __wake_up_q(struct wake_q_head *head, bool sleeper);
+static inline void wake_up_q(struct wake_q_head *head)
+{
+       __wake_up_q(head, false);
+}
+
+static inline void wake_up_q_sleeper(struct wake_q_head *head)
+{
+       __wake_up_q(head, true);
+}
 
 #endif /* _LINUX_SCHED_WAKE_Q_H */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f189a8a3bbb8..107079a2d7ed 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -221,20 +221,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
        return __read_seqcount_retry(s, start);
 }
 
-
-
-static inline void raw_write_seqcount_begin(seqcount_t *s)
+static inline void __raw_write_seqcount_begin(seqcount_t *s)
 {
        s->sequence++;
        smp_wmb();
 }
 
-static inline void raw_write_seqcount_end(seqcount_t *s)
+static inline void raw_write_seqcount_begin(seqcount_t *s)
+{
+       preempt_disable_rt();
+       __raw_write_seqcount_begin(s);
+}
+
+static inline void __raw_write_seqcount_end(seqcount_t *s)
 {
        smp_wmb();
        s->sequence++;
 }
 
+static inline void raw_write_seqcount_end(seqcount_t *s)
+{
+       __raw_write_seqcount_end(s);
+       preempt_enable_rt();
+}
+
 /**
  * raw_write_seqcount_barrier - do a seq write barrier
  * @s: pointer to seqcount_t
@@ -429,10 +439,33 @@ typedef struct {
 /*
  * Read side functions for starting and finalizing a read side section.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 static inline unsigned read_seqbegin(const seqlock_t *sl)
 {
        return read_seqcount_begin(&sl->seqcount);
 }
+#else
+/*
+ * Starvation safe read side for RT
+ */
+static inline unsigned read_seqbegin(seqlock_t *sl)
+{
+       unsigned ret;
+
+repeat:
+       ret = ACCESS_ONCE(sl->seqcount.sequence);
+       if (unlikely(ret & 1)) {
+               /*
+                * Take the lock and let the writer proceed (i.e. evtl
+                * boost it), otherwise we could loop here forever.
+                */
+               spin_unlock_wait(&sl->lock);
+               goto repeat;
+       }
+       smp_rmb();
+       return ret;
+}
+#endif
 
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
@@ -447,36 +480,45 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
        spin_lock(&sl->lock);
-       write_seqcount_begin(&sl->seqcount);
+       __raw_write_seqcount_begin(&sl->seqcount);
+}
+
+static inline int try_write_seqlock(seqlock_t *sl)
+{
+       if (spin_trylock(&sl->lock)) {
+               __raw_write_seqcount_begin(&sl->seqcount);
+               return 1;
+       }
+       return 0;
 }
 
 static inline void write_sequnlock(seqlock_t *sl)
 {
-       write_seqcount_end(&sl->seqcount);
+       __raw_write_seqcount_end(&sl->seqcount);
        spin_unlock(&sl->lock);
 }
 
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
        spin_lock_bh(&sl->lock);
-       write_seqcount_begin(&sl->seqcount);
+       __raw_write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-       write_seqcount_end(&sl->seqcount);
+       __raw_write_seqcount_end(&sl->seqcount);
        spin_unlock_bh(&sl->lock);
 }
 
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
        spin_lock_irq(&sl->lock);
-       write_seqcount_begin(&sl->seqcount);
+       __raw_write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-       write_seqcount_end(&sl->seqcount);
+       __raw_write_seqcount_end(&sl->seqcount);
        spin_unlock_irq(&sl->lock);
 }
 
@@ -485,7 +527,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
        unsigned long flags;
 
        spin_lock_irqsave(&sl->lock, flags);
-       write_seqcount_begin(&sl->seqcount);
+       __raw_write_seqcount_begin(&sl->seqcount);
        return flags;
 }
 
@@ -495,7 +537,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-       write_seqcount_end(&sl->seqcount);
+       __raw_write_seqcount_end(&sl->seqcount);
        spin_unlock_irqrestore(&sl->lock, flags);
 }
 
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 042968dd98f0..a7d20f85cc0e 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -243,6 +243,7 @@ static inline void init_sigpending(struct sigpending *sig)
 }
 
 extern void flush_sigqueue(struct sigpending *queue);
+extern void flush_task_sigqueue(struct task_struct *tsk);
 
 /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
 static inline int valid_signal(unsigned long sig)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f64e88444082..07576a062ac0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -287,6 +287,7 @@ struct sk_buff_head {
 
        __u32           qlen;
        spinlock_t      lock;
+       raw_spinlock_t  raw_lock;
 };
 
 struct sk_buff;
@@ -1672,6 +1673,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list)
        __skb_queue_head_init(list);
 }
 
+static inline void skb_queue_head_init_raw(struct sk_buff_head *list)
+{
+       raw_spin_lock_init(&list->raw_lock);
+       __skb_queue_head_init(list);
+}
+
 static inline void skb_queue_head_init_class(struct sk_buff_head *list,
                struct lock_class_key *class)
 {
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 9fb239e12b82..5801e516ba63 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -202,6 +202,9 @@ static inline int get_boot_cpu_id(void)
 #define get_cpu()              ({ preempt_disable(); smp_processor_id(); })
 #define put_cpu()              preempt_enable()
 
+#define get_cpu_light()                ({ migrate_disable(); smp_processor_id(); })
+#define put_cpu_light()                migrate_enable()
+
 /*
  * Callback to arch code if there's nosmp or maxcpus=0 on the
  * boot command line:
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 341e1a12bfc7..7c8f0a985b9e 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -286,7 +286,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 #define raw_spin_can_lock(lock)        (!raw_spin_is_locked(lock))
 
 /* Include rwlock functions */
-#include <linux/rwlock.h>
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/rwlock_rt.h>
+#else
+# include <linux/rwlock.h>
+#endif
 
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
@@ -297,6 +301,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # include <linux/spinlock_api_up.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_rt.h>
+#else /* PREEMPT_RT_FULL */
+
 /*
  * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
  */
@@ -421,4 +429,6 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
 #define atomic_dec_and_lock(atomic, lock) \
                __cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
 
+#endif /* !PREEMPT_RT_FULL */
+
 #endif /* __LINUX_SPINLOCK_H */
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 42dfab89e740..29d99ae5a8ab 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
        return 0;
 }
 
-#include <linux/rwlock_api_smp.h>
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/rwlock_api_smp.h>
+#endif
 
 #endif /* __LINUX_SPINLOCK_API_SMP_H */
diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
new file mode 100644
index 000000000000..c95e1f5145ac
--- /dev/null
+++ b/include/linux/spinlock_rt.h
@@ -0,0 +1,159 @@
+#ifndef __LINUX_SPINLOCK_RT_H
+#define __LINUX_SPINLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+#include <linux/bug.h>
+
+extern void
+__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key);
+
+#define spin_lock_init(slock)                          \
+do {                                                   \
+       static struct lock_class_key __key;             \
+                                                       \
+       rt_mutex_init(&(slock)->lock);                  \
+       __rt_spin_lock_init(slock, #slock, &__key);     \
+} while (0)
+
+extern void __lockfunc rt_spin_lock(spinlock_t *lock);
+extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
+extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
+extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
+extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
+extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
+extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
+extern int __lockfunc rt_spin_trylock(spinlock_t *lock);
+extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock);
+
+/*
+ * lockdep-less calls, for derived types like rwlock:
+ * (for trylock they can use rt_mutex_trylock() directly.
+ * Migrate disable handling must be done at the call site.
+ */
+extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_trylock(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
+
+#define spin_lock(lock)                        rt_spin_lock(lock)
+
+#define spin_lock_bh(lock)                     \
+       do {                                    \
+               local_bh_disable();             \
+               rt_spin_lock(lock);             \
+       } while (0)
+
+#define spin_lock_irq(lock)            spin_lock(lock)
+
+#define spin_do_trylock(lock)          __cond_lock(lock, rt_spin_trylock(lock))
+
+#define spin_trylock(lock)                     \
+({                                             \
+       int __locked;                           \
+       __locked = spin_do_trylock(lock);       \
+       __locked;                               \
+})
+
+#ifdef CONFIG_LOCKDEP
+# define spin_lock_nested(lock, subclass)              \
+       do {                                            \
+               rt_spin_lock_nested(lock, subclass);    \
+       } while (0)
+
+#define spin_lock_bh_nested(lock, subclass)            \
+       do {                                            \
+               local_bh_disable();                     \
+               rt_spin_lock_nested(lock, subclass);    \
+       } while (0)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+       do {                                             \
+               typecheck(unsigned long, flags);         \
+               flags = 0;                               \
+               rt_spin_lock_nested(lock, subclass);     \
+       } while (0)
+#else
+# define spin_lock_nested(lock, subclass)      spin_lock(lock)
+# define spin_lock_bh_nested(lock, subclass)   spin_lock_bh(lock)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+       do {                                             \
+               typecheck(unsigned long, flags);         \
+               flags = 0;                               \
+               spin_lock(lock);                         \
+       } while (0)
+#endif
+
+#define spin_lock_irqsave(lock, flags)                  \
+       do {                                             \
+               typecheck(unsigned long, flags);         \
+               flags = 0;                               \
+               spin_lock(lock);                         \
+       } while (0)
+
+static inline unsigned long spin_lock_trace_flags(spinlock_t *lock)
+{
+       unsigned long flags = 0;
+#ifdef CONFIG_TRACE_IRQFLAGS
+       flags = rt_spin_lock_trace_flags(lock);
+#else
+       spin_lock(lock); /* lock_local */
+#endif
+       return flags;
+}
+
+/* FIXME: we need rt_spin_lock_nest_lock */
+#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0)
+
+#define spin_unlock(lock)                      rt_spin_unlock(lock)
+
+#define spin_unlock_bh(lock)                           \
+       do {                                            \
+               rt_spin_unlock(lock);                   \
+               local_bh_enable();                      \
+       } while (0)
+
+#define spin_unlock_irq(lock)          spin_unlock(lock)
+
+#define spin_unlock_irqrestore(lock, flags)            \
+       do {                                            \
+               typecheck(unsigned long, flags);        \
+               (void) flags;                           \
+               spin_unlock(lock);                      \
+       } while (0)
+
+#define spin_trylock_bh(lock)  __cond_lock(lock, rt_spin_trylock_bh(lock))
+#define spin_trylock_irq(lock) spin_trylock(lock)
+
+#define spin_trylock_irqsave(lock, flags)      \
+       rt_spin_trylock_irqsave(lock, &(flags))
+
+#define spin_unlock_wait(lock)         rt_spin_unlock_wait(lock)
+
+#ifdef CONFIG_GENERIC_LOCKBREAK
+# define spin_is_contended(lock)       ((lock)->break_lock)
+#else
+# define spin_is_contended(lock)       (((void)(lock), 0))
+#endif
+
+static inline int spin_can_lock(spinlock_t *lock)
+{
+       return !rt_mutex_is_locked(&lock->lock);
+}
+
+static inline int spin_is_locked(spinlock_t *lock)
+{
+       return rt_mutex_is_locked(&lock->lock);
+}
+
+static inline void assert_spin_locked(spinlock_t *lock)
+{
+       BUG_ON(!spin_is_locked(lock));
+}
+
+#define atomic_dec_and_lock(atomic, lock) \
+       atomic_dec_and_spin_lock(atomic, lock)
+
+#endif
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 73548eb13a5d..10bac715ea96 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -9,80 +9,15 @@
  * Released under the General Public License (GPL).
  */
 
-#if defined(CONFIG_SMP)
-# include <asm/spinlock_types.h>
-#else
-# include <linux/spinlock_types_up.h>
-#endif
-
-#include <linux/lockdep.h>
-
-typedef struct raw_spinlock {
-       arch_spinlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
-       unsigned int break_lock;
-#endif
-#ifdef CONFIG_DEBUG_SPINLOCK
-       unsigned int magic, owner_cpu;
-       void *owner;
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-       struct lockdep_map dep_map;
-#endif
-} raw_spinlock_t;
-
-#define SPINLOCK_MAGIC         0xdead4ead
-
-#define SPINLOCK_OWNER_INIT    ((void *)-1L)
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SPIN_DEP_MAP_INIT(lockname)   .dep_map = { .name = #lockname }
-#else
-# define SPIN_DEP_MAP_INIT(lockname)
-#endif
+#include <linux/spinlock_types_raw.h>
 
-#ifdef CONFIG_DEBUG_SPINLOCK
-# define SPIN_DEBUG_INIT(lockname)             \
-       .magic = SPINLOCK_MAGIC,                \
-       .owner_cpu = -1,                        \
-       .owner = SPINLOCK_OWNER_INIT,
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_types_nort.h>
+# include <linux/rwlock_types.h>
 #else
-# define SPIN_DEBUG_INIT(lockname)
+# include <linux/rtmutex.h>
+# include <linux/spinlock_types_rt.h>
+# include <linux/rwlock_types_rt.h>
 #endif
 
-#define __RAW_SPIN_LOCK_INITIALIZER(lockname)  \
-       {                                       \
-       .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,  \
-       SPIN_DEBUG_INIT(lockname)               \
-       SPIN_DEP_MAP_INIT(lockname) }
-
-#define __RAW_SPIN_LOCK_UNLOCKED(lockname)     \
-       (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
-
-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
-
-typedef struct spinlock {
-       union {
-               struct raw_spinlock rlock;
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
-               struct {
-                       u8 __padding[LOCK_PADSIZE];
-                       struct lockdep_map dep_map;
-               };
-#endif
-       };
-} spinlock_t;
-
-#define __SPIN_LOCK_INITIALIZER(lockname) \
-       { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
-
-#define __SPIN_LOCK_UNLOCKED(lockname) \
-       (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
-
-#define DEFINE_SPINLOCK(x)     spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
-
-#include <linux/rwlock_types.h>
-
 #endif /* __LINUX_SPINLOCK_TYPES_H */
diff --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h
new file mode 100644
index 000000000000..f1dac1fb1d6a
--- /dev/null
+++ b/include/linux/spinlock_types_nort.h
@@ -0,0 +1,33 @@
+#ifndef __LINUX_SPINLOCK_TYPES_NORT_H
+#define __LINUX_SPINLOCK_TYPES_NORT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+/*
+ * The non RT version maps spinlocks to raw_spinlocks
+ */
+typedef struct spinlock {
+       union {
+               struct raw_spinlock rlock;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
+               struct {
+                       u8 __padding[LOCK_PADSIZE];
+                       struct lockdep_map dep_map;
+               };
+#endif
+       };
+} spinlock_t;
+
+#define __SPIN_LOCK_INITIALIZER(lockname) \
+       { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
+
+#define __SPIN_LOCK_UNLOCKED(lockname) \
+       (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
+
+#define DEFINE_SPINLOCK(x)     spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
+
+#endif
diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h
new file mode 100644
index 000000000000..03235b475b77
--- /dev/null
+++ b/include/linux/spinlock_types_raw.h
@@ -0,0 +1,58 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
+#define __LINUX_SPINLOCK_TYPES_RAW_H
+
+#include <linux/types.h>
+
+#if defined(CONFIG_SMP)
+# include <asm/spinlock_types.h>
+#else
+# include <linux/spinlock_types_up.h>
+#endif
+
+#include <linux/lockdep.h>
+
+typedef struct raw_spinlock {
+       arch_spinlock_t raw_lock;
+#ifdef CONFIG_GENERIC_LOCKBREAK
+       unsigned int break_lock;
+#endif
+#ifdef CONFIG_DEBUG_SPINLOCK
+       unsigned int magic, owner_cpu;
+       void *owner;
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       struct lockdep_map dep_map;
+#endif
+} raw_spinlock_t;
+
+#define SPINLOCK_MAGIC         0xdead4ead
+
+#define SPINLOCK_OWNER_INIT    ((void *)-1L)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define SPIN_DEP_MAP_INIT(lockname)   .dep_map = { .name = #lockname }
+#else
+# define SPIN_DEP_MAP_INIT(lockname)
+#endif
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+# define SPIN_DEBUG_INIT(lockname)             \
+       .magic = SPINLOCK_MAGIC,                \
+       .owner_cpu = -1,                        \
+       .owner = SPINLOCK_OWNER_INIT,
+#else
+# define SPIN_DEBUG_INIT(lockname)
+#endif
+
+#define __RAW_SPIN_LOCK_INITIALIZER(lockname)  \
+       {                                       \
+       .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,  \
+       SPIN_DEBUG_INIT(lockname)               \
+       SPIN_DEP_MAP_INIT(lockname) }
+
+#define __RAW_SPIN_LOCK_UNLOCKED(lockname)     \
+       (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
+
+#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
+
+#endif
diff --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h
new file mode 100644
index 000000000000..3e3d8c5f7a9a
--- /dev/null
+++ b/include/linux/spinlock_types_rt.h
@@ -0,0 +1,48 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RT_H
+#define __LINUX_SPINLOCK_TYPES_RT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+#include <linux/cache.h>
+
+/*
+ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field:
+ */
+typedef struct spinlock {
+       struct rt_mutex         lock;
+       unsigned int            break_lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       struct lockdep_map      dep_map;
+#endif
+} spinlock_t;
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define __RT_SPIN_INITIALIZER(name) \
+       { \
+       .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
+       .save_state = 1, \
+       .file = __FILE__, \
+       .line = __LINE__ , \
+       }
+#else
+# define __RT_SPIN_INITIALIZER(name) \
+       {                                                               \
+       .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),          \
+       .save_state = 1, \
+       }
+#endif
+
+/*
+.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock)
+*/
+
+#define __SPIN_LOCK_UNLOCKED(name)                     \
+       { .lock = __RT_SPIN_INITIALIZER(name.lock),             \
+         SPIN_DEP_MAP_INIT(name) }
+
+#define DEFINE_SPINLOCK(name) \
+       spinlock_t name = __SPIN_LOCK_UNLOCKED(name)
+
+#endif
diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h
index c09b6407ae1b..b0243ba07fb7 100644
--- a/include/linux/spinlock_types_up.h
+++ b/include/linux/spinlock_types_up.h
@@ -1,10 +1,6 @@
 #ifndef __LINUX_SPINLOCK_TYPES_UP_H
 #define __LINUX_SPINLOCK_TYPES_UP_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 /*
  * include/linux/spinlock_types_up.h - spinlock type definitions for UP
  *
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 261471f407a5..f41d2fb09f87 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -43,7 +43,7 @@ struct srcu_struct {
 
 void srcu_drive_gp(struct work_struct *wp);
 
-#define __SRCU_STRUCT_INIT(name)                                       \
+#define __SRCU_STRUCT_INIT(name, __ignored)                            \
 {                                                                      \
        .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq),        \
        .srcu_cb_tail = &name.srcu_cb_head,                             \
@@ -56,9 +56,9 @@ void srcu_drive_gp(struct work_struct *wp);
  * Tree SRCU, which needs some per-CPU data.
  */
 #define DEFINE_SRCU(name) \
-       struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+       struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
 #define DEFINE_STATIC_SRCU(name) \
-       static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+       static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
 
 void synchronize_srcu(struct srcu_struct *sp);
 
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index a949f4f9e4d7..745d4ca4dd50 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -40,7 +40,7 @@ struct srcu_data {
        unsigned long srcu_unlock_count[2];     /* Unlocks per CPU. */
 
        /* Update-side state. */
-       raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp;
+       spinlock_t __private lock ____cacheline_internodealigned_in_smp;
        struct rcu_segcblist srcu_cblist;       /* List of callbacks.*/
        unsigned long srcu_gp_seq_needed;       /* Furthest future GP needed. */
        unsigned long srcu_gp_seq_needed_exp;   /* Furthest future exp GP. */
@@ -58,7 +58,7 @@ struct srcu_data {
  * Node in SRCU combining tree, similar in function to rcu_data.
  */
 struct srcu_node {
-       raw_spinlock_t __private lock;
+       spinlock_t __private lock;
        unsigned long srcu_have_cbs[4];         /* GP seq for children */
                                                /*  having CBs, but only */
                                                /*  is > ->srcu_gq_seq. */
@@ -78,7 +78,7 @@ struct srcu_struct {
        struct srcu_node *level[RCU_NUM_LVLS + 1];
                                                /* First node at each level. */
        struct mutex srcu_cb_mutex;             /* Serialize CB preparation. */
-       raw_spinlock_t __private lock;          /* Protect counters */
+       spinlock_t __private lock;              /* Protect counters */
        struct mutex srcu_gp_mutex;             /* Serialize GP work. */
        unsigned int srcu_idx;                  /* Current rdr array element. */
        unsigned long srcu_gp_seq;              /* Grace-period seq #. */
@@ -104,10 +104,10 @@ struct srcu_struct {
 #define SRCU_STATE_SCAN1       1
 #define SRCU_STATE_SCAN2       2
 
-#define __SRCU_STRUCT_INIT(name)                                       \
+#define __SRCU_STRUCT_INIT(name, pcpu_name)                            \
        {                                                               \
-               .sda = &name##_srcu_data,                               \
-               .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock),            \
+               .sda = &pcpu_name,                                      \
+               .lock = __SPIN_LOCK_UNLOCKED(name.lock),                \
                .srcu_gp_seq_needed = 0 - 1,                            \
                __SRCU_DEP_MAP_INIT(name)                               \
        }
@@ -133,7 +133,7 @@ struct srcu_struct {
  */
 #define __DEFINE_SRCU(name, is_static)                                 \
        static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
-       is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+       is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_data)
 #define DEFINE_SRCU(name)              __DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)       __DEFINE_SRCU(name, static)
 
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 8544357d92d0..616ea66cd283 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -196,6 +196,12 @@ struct platform_s2idle_ops {
        void (*end)(void);
 };
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern bool pm_in_action;
+#else
+# define pm_in_action false
+#endif
+
 #ifdef CONFIG_SUSPEND
 extern suspend_state_t mem_sleep_current;
 extern suspend_state_t mem_sleep_default;
diff --git a/include/linux/swait.h b/include/linux/swait.h
index c98aaf677466..853f3e61a9f4 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
+#include <linux/wait.h>
 #include <asm/current.h>
 
 /*
@@ -147,6 +148,7 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 extern void swake_up(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
+extern void swake_up_all_locked(struct swait_queue_head *q);
 
 extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f02fb5db8914..6c775168df67 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -12,6 +12,7 @@
 #include <linux/fs.h>
 #include <linux/atomic.h>
 #include <linux/page-flags.h>
+#include <linux/locallock.h>
 #include <asm/page.h>
 
 struct notifier_block;
@@ -297,7 +298,8 @@ struct vma_swap_readahead {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
-void workingset_update_node(struct radix_tree_node *node, void *private);
+void __workingset_update_node(struct radix_tree_node *node, void *private);
+DECLARE_LOCAL_IRQ_LOCK(shadow_nodes_lock);
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
@@ -310,6 +312,7 @@ extern unsigned long nr_free_pagecache_pages(void);
 
 
 /* linux/mm/swap.c */
+DECLARE_LOCAL_IRQ_LOCK(swapvec_lock);
 extern void lru_cache_add(struct page *);
 extern void lru_cache_add_anon(struct page *page);
 extern void lru_cache_add_file(struct page *page);
diff --git a/include/linux/swork.h b/include/linux/swork.h
new file mode 100644
index 000000000000..f175fa9a6016
--- /dev/null
+++ b/include/linux/swork.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SWORK_H
+#define _LINUX_SWORK_H
+
+#include <linux/list.h>
+
+struct swork_event {
+       struct list_head item;
+       unsigned long flags;
+       void (*func)(struct swork_event *);
+};
+
+static inline void INIT_SWORK(struct swork_event *event,
+                             void (*func)(struct swork_event *))
+{
+       event->flags = 0;
+       event->func = func;
+}
+
+bool swork_queue(struct swork_event *sev);
+
+int swork_get(void);
+void swork_put(void);
+
+#endif /* _LINUX_SWORK_H */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index cf2862bd134a..fd05d83740df 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -86,7 +86,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
        test_ti_thread_flag(current_thread_info(), flag)
 
-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+#ifdef CONFIG_PREEMPT_LAZY
+#define tif_need_resched()     (test_thread_flag(TIF_NEED_RESCHED) || \
+                                test_thread_flag(TIF_NEED_RESCHED_LAZY))
+#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED))
+#define tif_need_resched_lazy()        test_thread_flag(TIF_NEED_RESCHED_LAZY))
+
+#else
+#define tif_need_resched()     test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_lazy()        0
+#endif
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
 static inline int arch_within_stack_frames(const void * const stack,
diff --git a/include/linux/timer.h b/include/linux/timer.h
index e0ea1fe87572..df3085ddf662 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -213,7 +213,7 @@ extern void add_timer(struct timer_list *timer);
 
 extern int try_to_del_timer_sync(struct timer_list *timer);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
   extern int del_timer_sync(struct timer_list *timer);
 #else
 # define del_timer_sync(t)             del_timer(t)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2bcb4dc6df1a..edd1e42e8a2f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -62,6 +62,9 @@ struct trace_entry {
        unsigned char           flags;
        unsigned char           preempt_count;
        int                     pid;
+       unsigned short          migrate_disable;
+       unsigned short          padding;
+       unsigned char           preempt_lazy_count;
 };
 
 #define TRACE_EVENT_TYPE_MAX                                           \
@@ -402,11 +405,13 @@ enum event_trigger_type {
 
 extern int filter_match_preds(struct event_filter *filter, void *rec);
 
-extern enum event_trigger_type event_triggers_call(struct trace_event_file *file,
-                                                  void *rec);
-extern void event_triggers_post_call(struct trace_event_file *file,
-                                    enum event_trigger_type tt,
-                                    void *rec);
+extern enum event_trigger_type
+event_triggers_call(struct trace_event_file *file, void *rec,
+                   struct ring_buffer_event *event);
+extern void
+event_triggers_post_call(struct trace_event_file *file,
+                        enum event_trigger_type tt,
+                        void *rec, struct ring_buffer_event *event);
 
 bool trace_event_ignore_this_pid(struct trace_event_file *trace_file);
 
@@ -426,7 +431,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file)
 
        if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) {
                if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
-                       event_triggers_call(file, NULL);
+                       event_triggers_call(file, NULL, NULL);
                if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
                        return true;
                if (eflags & EVENT_FILE_FL_PID_FILTER)
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 251e655d407f..57e8e32ef2b0 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -185,6 +185,7 @@ static __always_inline void pagefault_disabled_dec(void)
  */
 static inline void pagefault_disable(void)
 {
+       migrate_disable();
        pagefault_disabled_inc();
        /*
         * make sure to have issued the store before a pagefault
@@ -201,6 +202,7 @@ static inline void pagefault_enable(void)
         */
        barrier();
        pagefault_disabled_dec();
+       migrate_enable();
 }
 
 /*
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 1e0cb72e0598..87ab0996a9b0 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -33,7 +33,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
  */
 static inline void __count_vm_event(enum vm_event_item item)
 {
+       preempt_disable_rt();
        raw_cpu_inc(vm_event_states.event[item]);
+       preempt_enable_rt();
 }
 
 static inline void count_vm_event(enum vm_event_item item)
@@ -43,7 +45,9 @@ static inline void count_vm_event(enum vm_event_item item)
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
+       preempt_disable_rt();
        raw_cpu_add(vm_event_states.event[item], delta);
+       preempt_enable_rt();
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 158715445ffb..3451706a3074 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -10,6 +10,7 @@
 
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
+#include <linux/atomic.h>
 
 typedef struct wait_queue_entry wait_queue_entry_t;
 
@@ -486,8 +487,8 @@ do {                                                                                \
        int __ret = 0;                                                          \
        struct hrtimer_sleeper __t;                                             \
                                                                                \
-       hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);   \
-       hrtimer_init_sleeper(&__t, current);                                    \
+       hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, HRTIMER_MODE_REL,  \
+                                     current);                                 \
        if ((timeout) != KTIME_MAX)                                             \
                hrtimer_start_range_ns(&__t.timer, timeout,                     \
                                       current->timer_slack_ns,                 \
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 304f7aa9cc01..00d3813cef26 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -6,6 +6,7 @@
 #include <linux/socket.h>
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
+#include <net/net_seq_lock.h>
 
 struct gnet_stats_basic_cpu {
        struct gnet_stats_basic_packed bstats;
@@ -36,11 +37,11 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
                                 spinlock_t *lock, struct gnet_dump *d,
                                 int padattr);
 
-int gnet_stats_copy_basic(const seqcount_t *running,
+int gnet_stats_copy_basic(net_seqlock_t *running,
                          struct gnet_dump *d,
                          struct gnet_stats_basic_cpu __percpu *cpu,
                          struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(const seqcount_t *running,
+void __gnet_stats_copy_basic(net_seqlock_t *running,
                             struct gnet_stats_basic_packed *bstats,
                             struct gnet_stats_basic_cpu __percpu *cpu,
                             struct gnet_stats_basic_packed *b);
@@ -57,13 +58,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
                      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
                      struct net_rate_estimator __rcu **rate_est,
                      spinlock_t *stats_lock,
-                     seqcount_t *running, struct nlattr *opt);
+                     net_seqlock_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
                          struct gnet_stats_basic_cpu __percpu *cpu_bstats,
                          struct net_rate_estimator __rcu **ptr,
                          spinlock_t *stats_lock,
-                         seqcount_t *running, struct nlattr *opt);
+                         net_seqlock_t *running, struct nlattr *opt);
 bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
 bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
                        struct gnet_stats_rate_est64 *sample);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index a964366a7ef5..51c854583987 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -450,7 +450,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 }
 #endif
 
-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
+static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
 {
        unsigned int seq;
        unsigned int hh_len;
@@ -474,7 +474,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 
 static inline int neigh_output(struct neighbour *n, struct sk_buff *skb)
 {
-       const struct hh_cache *hh = &n->hh;
+       struct hh_cache *hh = &n->hh;
 
        if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
                return neigh_hh_output(hh, skb);
@@ -515,7 +515,7 @@ struct neighbour_cb {
 
 #define NEIGH_CB(skb)  ((struct neighbour_cb *)(skb)->cb)
 
-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
+static inline void neigh_ha_snapshot(char *dst, struct neighbour *n,
                                     const struct net_device *dev)
 {
        unsigned int seq;
diff --git a/include/net/net_seq_lock.h b/include/net/net_seq_lock.h
new file mode 100644
index 000000000000..a7034298a82a
--- /dev/null
+++ b/include/net/net_seq_lock.h
@@ -0,0 +1,15 @@
+#ifndef __NET_NET_SEQ_LOCK_H__
+#define __NET_NET_SEQ_LOCK_H__
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define net_seqlock_t                 seqlock_t
+# define net_seq_begin(__r)            read_seqbegin(__r)
+# define net_seq_retry(__r, __s)       read_seqretry(__r, __s)
+
+#else
+# define net_seqlock_t                 seqcount_t
+# define net_seq_begin(__r)            read_seqcount_begin(__r)
+# define net_seq_retry(__r, __s)       read_seqcount_retry(__r, __s)
+#endif
+
+#endif
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f59acacaa265..6ac7c3659973 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -10,6 +10,7 @@
 #include <linux/percpu.h>
 #include <linux/dynamic_queue_limits.h>
 #include <linux/list.h>
+#include <net/net_seq_lock.h>
 #include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include <net/gen_stats.h>
@@ -90,7 +91,7 @@ struct Qdisc {
        struct sk_buff          *gso_skb ____cacheline_aligned_in_smp;
        struct qdisc_skb_head   q;
        struct gnet_stats_basic_packed bstats;
-       seqcount_t              running;
+       net_seqlock_t           running;
        struct gnet_stats_queue qstats;
        unsigned long           state;
        struct Qdisc            *next_sched;
@@ -109,13 +110,22 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
        refcount_inc(&qdisc->refcnt);
 }
 
-static inline bool qdisc_is_running(const struct Qdisc *qdisc)
+static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+       return spin_is_locked(&qdisc->running.lock) ? true : false;
+#else
        return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
+#endif
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+       if (try_write_seqlock(&qdisc->running))
+               return true;
+       return false;
+#else
        if (qdisc_is_running(qdisc))
                return false;
        /* Variant of write_seqcount_begin() telling lockdep a trylock
@@ -124,11 +134,16 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
        raw_write_seqcount_begin(&qdisc->running);
        seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
        return true;
+#endif
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+       write_sequnlock(&qdisc->running);
+#else
        write_seqcount_end(&qdisc->running);
+#endif
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
@@ -337,7 +352,7 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc)
        return qdisc_lock(root);
 }
 
-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
+static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
 {
        struct Qdisc *root = qdisc_root_sleeping(qdisc);
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index db99efb2d1d0..a7b95ffbbf8b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -217,7 +217,7 @@ struct xfrm_state {
        struct xfrm_stats       stats;
 
        struct xfrm_lifetime_cur curlft;
-       struct tasklet_hrtimer  mtimer;
+       struct hrtimer          mtimer;
 
        struct xfrm_state_offload xso;
 
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index c6f728037c53..a57e4ee989d6 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -148,7 +148,11 @@ DEFINE_EVENT(timer_class, timer_cancel,
                { HRTIMER_MODE_ABS,             "ABS"           },      \
                { HRTIMER_MODE_REL,             "REL"           },      \
                { HRTIMER_MODE_ABS_PINNED,      "ABS|PINNED"    },      \
-               { HRTIMER_MODE_REL_PINNED,      "REL|PINNED"    })
+               { HRTIMER_MODE_REL_PINNED,      "REL|PINNED"    },      \
+               { HRTIMER_MODE_ABS_SOFT,        "ABS|SOFT"      },      \
+               { HRTIMER_MODE_REL_SOFT,        "REL|SOFT"      },      \
+               { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" },    \
+               { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" })
 
 /**
  * hrtimer_init - called when the hrtimer is initialized
@@ -186,15 +190,16 @@ TRACE_EVENT(hrtimer_init,
  */
 TRACE_EVENT(hrtimer_start,
 
-       TP_PROTO(struct hrtimer *hrtimer),
+       TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode),
 
-       TP_ARGS(hrtimer),
+       TP_ARGS(hrtimer, mode),
 
        TP_STRUCT__entry(
                __field( void *,        hrtimer         )
                __field( void *,        function        )
                __field( s64,           expires         )
                __field( s64,           softexpires     )
+               __field( enum hrtimer_mode,     mode    )
        ),
 
        TP_fast_assign(
@@ -202,12 +207,14 @@ TRACE_EVENT(hrtimer_start,
                __entry->function       = hrtimer->function;
                __entry->expires        = hrtimer_get_expires(hrtimer);
                __entry->softexpires    = hrtimer_get_softexpires(hrtimer);
+               __entry->mode           = mode;
        ),
 
-       TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu",
-                 __entry->hrtimer, __entry->function,
+       TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+                 "mode=%s", __entry->hrtimer, __entry->function,
                  (unsigned long long) __entry->expires,
-                 (unsigned long long) __entry->softexpires)
+                 (unsigned long long) __entry->softexpires,
+                 decode_hrtimer_mode(__entry->mode))
 );
 
 /**
diff --git a/init/Kconfig b/init/Kconfig
index 46075327c165..a7aff2c1a203 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -744,6 +744,7 @@ config CFS_BANDWIDTH
 config RT_GROUP_SCHED
        bool "Group scheduling for SCHED_RR/FIFO"
        depends on CGROUP_SCHED
+       depends on !PREEMPT_RT_FULL
        default n
        help
          This feature lets you explicitly allocate real CPU bandwidth
@@ -1533,6 +1534,7 @@ choice
 
 config SLAB
        bool "SLAB"
+       depends on !PREEMPT_RT_FULL
        select HAVE_HARDENED_USERCOPY_ALLOCATOR
        help
          The regular slab allocator that is established and known to work
@@ -1553,6 +1555,7 @@ config SLUB
 config SLOB
        depends on EXPERT
        bool "SLOB (Simple Allocator)"
+       depends on !PREEMPT_RT_FULL
        help
           SLOB replaces the stock allocator with a drastically simpler
           allocator. SLOB is generally more space efficient but
@@ -1594,7 +1597,7 @@ config SLAB_FREELIST_HARDENED
 
 config SLUB_CPU_PARTIAL
        default y
-       depends on SLUB && SMP
+       depends on SLUB && SMP && !PREEMPT_RT_FULL
        bool "SLUB per cpu partial cache"
        help
          Per cpu partial caches accellerate objects allocation and freeing
diff --git a/init/Makefile b/init/Makefile
index 1dbb23787290..eabf3f1b14be 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -36,4 +36,4 @@ silent_chk_compile.h = :
 include/generated/compile.h: FORCE
        @$($(quiet)chk_compile.h)
        $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
-       "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)"
+       "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)"
diff --git a/init/main.c b/init/main.c
index c4a45145e102..c86f3d3b9a72 100644
--- a/init/main.c
+++ b/init/main.c
@@ -543,6 +543,7 @@ asmlinkage __visible void __init start_kernel(void)
        setup_command_line(command_line);
        setup_nr_cpu_ids();
        setup_per_cpu_areas();
+       softirq_early_init();
        smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
        boot_cpu_hotplug_init();
 
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 84d882f3e299..af27c4000812 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW
 
 config MUTEX_SPIN_ON_OWNER
        def_bool y
-       depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
+       depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
 
 config RWSEM_SPIN_ON_OWNER
        def_bool y
-       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
+       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
 
 config LOCK_SPIN_ON_OWNER
        def_bool y
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 3f9c97419f02..11dbe26a8279 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -1,3 +1,16 @@
+config PREEMPT
+       bool
+       select PREEMPT_COUNT
+
+config PREEMPT_RT_BASE
+       bool
+       select PREEMPT
+
+config HAVE_PREEMPT_LAZY
+       bool
+
+config PREEMPT_LAZY
+       def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL
 
 choice
        prompt "Preemption Model"
@@ -33,9 +46,9 @@ config PREEMPT_VOLUNTARY
 
          Select this if you are building a kernel for a desktop system.
 
-config PREEMPT
+config PREEMPT__LL
        bool "Preemptible Kernel (Low-Latency Desktop)"
-       select PREEMPT_COUNT
+       select PREEMPT
        select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
        help
          This option reduces the latency of the kernel by making
@@ -52,6 +65,22 @@ config PREEMPT
          embedded system with latency requirements in the milliseconds
          range.
 
+config PREEMPT_RTB
+       bool "Preemptible Kernel (Basic RT)"
+       select PREEMPT_RT_BASE
+       help
+         This option is basically the same as (Low-Latency Desktop) but
+         enables changes which are preliminary for the full preemptible
+         RT kernel.
+
+config PREEMPT_RT_FULL
+       bool "Fully Preemptible Kernel (RT)"
+       depends on IRQ_FORCED_THREADING
+       select PREEMPT_RT_BASE
+       select PREEMPT_RCU
+       help
+         All and everything
+
 endchoice
 
 config PREEMPT_COUNT
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3fc11b8851ac..a04c3aded76b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4515,10 +4515,10 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
        queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-static void css_release_work_fn(struct work_struct *work)
+static void css_release_work_fn(struct swork_event *sev)
 {
        struct cgroup_subsys_state *css =
-               container_of(work, struct cgroup_subsys_state, destroy_work);
+               container_of(sev, struct cgroup_subsys_state, destroy_swork);
        struct cgroup_subsys *ss = css->ss;
        struct cgroup *cgrp = css->cgroup;
 
@@ -4569,8 +4569,8 @@ static void css_release(struct percpu_ref *ref)
        struct cgroup_subsys_state *css =
                container_of(ref, struct cgroup_subsys_state, refcnt);
 
-       INIT_WORK(&css->destroy_work, css_release_work_fn);
-       queue_work(cgroup_destroy_wq, &css->destroy_work);
+       INIT_SWORK(&css->destroy_swork, css_release_work_fn);
+       swork_queue(&css->destroy_swork);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5276,6 +5276,7 @@ static int __init cgroup_wq_init(void)
         */
        cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
        BUG_ON(!cgroup_destroy_wq);
+       BUG_ON(swork_get());
        return 0;
 }
 core_initcall(cgroup_wq_init);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4657e2924ecb..bda2af78277a 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -288,7 +288,7 @@ static struct cpuset top_cpuset = {
  */
 
 static DEFINE_MUTEX(cpuset_mutex);
-static DEFINE_SPINLOCK(callback_lock);
+static DEFINE_RAW_SPINLOCK(callback_lock);
 
 static struct workqueue_struct *cpuset_migrate_mm_wq;
 
@@ -926,9 +926,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
                        continue;
                rcu_read_unlock();
 
-               spin_lock_irq(&callback_lock);
+               raw_spin_lock_irq(&callback_lock);
                cpumask_copy(cp->effective_cpus, new_cpus);
-               spin_unlock_irq(&callback_lock);
+               raw_spin_unlock_irq(&callback_lock);
 
                WARN_ON(!is_in_v2_mode() &&
                        !cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
@@ -993,9 +993,9 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
        if (retval < 0)
                return retval;
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 
        /* use trialcs->cpus_allowed as a temp variable */
        update_cpumasks_hier(cs, trialcs->cpus_allowed);
@@ -1179,9 +1179,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
                        continue;
                rcu_read_unlock();
 
-               spin_lock_irq(&callback_lock);
+               raw_spin_lock_irq(&callback_lock);
                cp->effective_mems = *new_mems;
-               spin_unlock_irq(&callback_lock);
+               raw_spin_unlock_irq(&callback_lock);
 
                WARN_ON(!is_in_v2_mode() &&
                        !nodes_equal(cp->mems_allowed, cp->effective_mems));
@@ -1249,9 +1249,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
        if (retval < 0)
                goto done;
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        cs->mems_allowed = trialcs->mems_allowed;
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 
        /* use trialcs->mems_allowed as a temp variable */
        update_nodemasks_hier(cs, &trialcs->mems_allowed);
@@ -1342,9 +1342,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
        spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
                        || (is_spread_page(cs) != is_spread_page(trialcs)));
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        cs->flags = trialcs->flags;
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 
        if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
                rebuild_sched_domains_locked();
@@ -1759,7 +1759,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
        cpuset_filetype_t type = seq_cft(sf)->private;
        int ret = 0;
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
 
        switch (type) {
        case FILE_CPULIST:
@@ -1778,7 +1778,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
                ret = -EINVAL;
        }
 
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
        return ret;
 }
 
@@ -1993,12 +1993,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
        cpuset_inc();
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        if (is_in_v2_mode()) {
                cpumask_copy(cs->effective_cpus, parent->effective_cpus);
                cs->effective_mems = parent->effective_mems;
        }
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 
        if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
                goto out_unlock;
@@ -2025,12 +2025,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
        }
        rcu_read_unlock();
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        cs->mems_allowed = parent->mems_allowed;
        cs->effective_mems = parent->mems_allowed;
        cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
        cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 out_unlock:
        mutex_unlock(&cpuset_mutex);
        return 0;
@@ -2069,7 +2069,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 static void cpuset_bind(struct cgroup_subsys_state *root_css)
 {
        mutex_lock(&cpuset_mutex);
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
 
        if (is_in_v2_mode()) {
                cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
@@ -2080,7 +2080,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
                top_cpuset.mems_allowed = top_cpuset.effective_mems;
        }
 
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
        mutex_unlock(&cpuset_mutex);
 }
 
@@ -2094,7 +2094,7 @@ static void cpuset_fork(struct task_struct *task)
        if (task_css_is_root(task, cpuset_cgrp_id))
                return;
 
-       set_cpus_allowed_ptr(task, &current->cpus_allowed);
+       set_cpus_allowed_ptr(task, current->cpus_ptr);
        task->mems_allowed = current->mems_allowed;
 }
 
@@ -2178,12 +2178,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 {
        bool is_empty;
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        cpumask_copy(cs->cpus_allowed, new_cpus);
        cpumask_copy(cs->effective_cpus, new_cpus);
        cs->mems_allowed = *new_mems;
        cs->effective_mems = *new_mems;
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 
        /*
         * Don't call update_tasks_cpumask() if the cpuset becomes empty,
@@ -2220,10 +2220,10 @@ hotplug_update_tasks(struct cpuset *cs,
        if (nodes_empty(*new_mems))
                *new_mems = parent_cs(cs)->effective_mems;
 
-       spin_lock_irq(&callback_lock);
+       raw_spin_lock_irq(&callback_lock);
        cpumask_copy(cs->effective_cpus, new_cpus);
        cs->effective_mems = *new_mems;
-       spin_unlock_irq(&callback_lock);
+       raw_spin_unlock_irq(&callback_lock);
 
        if (cpus_updated)
                update_tasks_cpumask(cs);
@@ -2316,21 +2316,21 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 
        /* synchronize cpus_allowed to cpu_active_mask */
        if (cpus_updated) {
-               spin_lock_irq(&callback_lock);
+               raw_spin_lock_irq(&callback_lock);
                if (!on_dfl)
                        cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
                cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
-               spin_unlock_irq(&callback_lock);
+               raw_spin_unlock_irq(&callback_lock);
                /* we don't mess with cpumasks of tasks in top_cpuset */
        }
 
        /* synchronize mems_allowed to N_MEMORY */
        if (mems_updated) {
-               spin_lock_irq(&callback_lock);
+               raw_spin_lock_irq(&callback_lock);
                if (!on_dfl)
                        top_cpuset.mems_allowed = new_mems;
                top_cpuset.effective_mems = new_mems;
-               spin_unlock_irq(&callback_lock);
+               raw_spin_unlock_irq(&callback_lock);
                update_tasks_nodemask(&top_cpuset);
        }
 
@@ -2429,11 +2429,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
        unsigned long flags;
 
-       spin_lock_irqsave(&callback_lock, flags);
+       raw_spin_lock_irqsave(&callback_lock, flags);
        rcu_read_lock();
        guarantee_online_cpus(task_cs(tsk), pmask);
        rcu_read_unlock();
-       spin_unlock_irqrestore(&callback_lock, flags);
+       raw_spin_unlock_irqrestore(&callback_lock, flags);
 }
 
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
@@ -2481,11 +2481,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
        nodemask_t mask;
        unsigned long flags;
 
-       spin_lock_irqsave(&callback_lock, flags);
+       raw_spin_lock_irqsave(&callback_lock, flags);
        rcu_read_lock();
        guarantee_online_mems(task_cs(tsk), &mask);
        rcu_read_unlock();
-       spin_unlock_irqrestore(&callback_lock, flags);
+       raw_spin_unlock_irqrestore(&callback_lock, flags);
 
        return mask;
 }
@@ -2577,14 +2577,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
                return true;
 
        /* Not hardwall and node outside mems_allowed: scan up cpusets */
-       spin_lock_irqsave(&callback_lock, flags);
+       raw_spin_lock_irqsave(&callback_lock, flags);
 
        rcu_read_lock();
        cs = nearest_hardwall_ancestor(task_cs(current));
        allowed = node_isset(node, cs->mems_allowed);
        rcu_read_unlock();
 
-       spin_unlock_irqrestore(&callback_lock, flags);
+       raw_spin_unlock_irqrestore(&callback_lock, flags);
        return allowed;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f3f389e33343..7d777b62e4eb 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -74,6 +74,11 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
        .fail = CPUHP_INVALID,
 };
 
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PREEMPT_RT_FULL)
+static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \
+       __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock);
+#endif
+
 #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
 static struct lockdep_map cpuhp_state_up_map =
        STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
@@ -287,6 +292,55 @@ static int cpu_hotplug_disabled;
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+/**
+ * pin_current_cpu - Prevent the current cpu from being unplugged
+ */
+void pin_current_cpu(void)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct rt_rw_lock *cpuhp_pin;
+       unsigned int cpu;
+       int ret;
+
+again:
+       cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock);
+       ret = __read_rt_trylock(cpuhp_pin);
+       if (ret) {
+               current->pinned_on_cpu = smp_processor_id();
+               return;
+       }
+       cpu = smp_processor_id();
+       preempt_lazy_enable();
+       preempt_enable();
+
+       __read_rt_lock(cpuhp_pin);
+
+       preempt_disable();
+       preempt_lazy_disable();
+       if (cpu != smp_processor_id()) {
+               __read_rt_unlock(cpuhp_pin);
+               goto again;
+       }
+       current->pinned_on_cpu = cpu;
+#endif
+}
+
+/**
+ * unpin_current_cpu - Allow unplug of current cpu
+ */
+void unpin_current_cpu(void)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock);
+
+       if (WARN_ON(current->pinned_on_cpu != smp_processor_id()))
+               cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, current->pinned_on_cpu);
+
+       current->pinned_on_cpu = -1;
+       __read_rt_unlock(cpuhp_pin);
+#endif
+}
+
 DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
 
 void cpus_read_lock(void)
@@ -843,6 +897,9 @@ static int take_cpu_down(void *_param)
 
 static int takedown_cpu(unsigned int cpu)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu);
+#endif
        struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
        int err;
 
@@ -855,11 +912,18 @@ static int takedown_cpu(unsigned int cpu)
         */
        irq_lock_sparse();
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+       __write_rt_lock(cpuhp_pin);
+#endif
+
        /*
         * So now all preempt/rcu users must observe !cpu_active().
         */
        err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
        if (err) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+               __write_rt_unlock(cpuhp_pin);
+#endif
                /* CPU refused to die */
                irq_unlock_sparse();
                /* Unpark the hotplug thread so we can rollback there */
@@ -878,6 +942,9 @@ static int takedown_cpu(unsigned int cpu)
        wait_for_ap_thread(st, false);
        BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+       __write_rt_unlock(cpuhp_pin);
+#endif
        /* Interrupts are moved away from the dying cpu, reenable alloc/free */
        irq_unlock_sparse();
 
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index ed5d34925ad0..c0d4c24fc241 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -854,9 +854,11 @@ int kdb_printf(const char *fmt, ...)
        va_list ap;
        int r;
 
+       kdb_trap_printk++;
        va_start(ap, fmt);
        r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap);
        va_end(ap);
+       kdb_trap_printk--;
 
        return r;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4dbce29a9313..de3d23bae9bf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1065,7 +1065,7 @@ static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
        cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
 
        raw_spin_lock_init(&cpuctx->hrtimer_lock);
-       hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+       hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
        timer->function = perf_mux_hrtimer_handler;
 }
 
@@ -8760,7 +8760,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event)
        if (!is_sampling_event(event))
                return;
 
-       hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
        hwc->hrtimer.function = perf_swevent_hrtimer;
 
        /*
diff --git a/kernel/exit.c b/kernel/exit.c
index e3a08761eb40..26f3b352b37a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -159,7 +159,7 @@ static void __exit_signal(struct task_struct *tsk)
         * Do this under ->siglock, we can race with another thread
         * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
         */
-       flush_sigqueue(&tsk->pending);
+       flush_task_sigqueue(tsk);
        tsk->sighand = NULL;
        spin_unlock(&sighand->siglock);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 6a219fea4926..bc849ac60aa6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -40,6 +40,7 @@
 #include <linux/hmm.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/kprobes.h>
 #include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
@@ -407,13 +408,24 @@ static inline void put_signal_struct(struct signal_struct *sig)
        if (atomic_dec_and_test(&sig->sigcnt))
                free_signal_struct(sig);
 }
-
+#ifdef CONFIG_PREEMPT_RT_BASE
+static
+#endif
 void __put_task_struct(struct task_struct *tsk)
 {
        WARN_ON(!tsk->exit_state);
        WARN_ON(atomic_read(&tsk->usage));
        WARN_ON(tsk == current);
 
+       /*
+        * Remove function-return probe instances associated with this
+        * task and put them back on the free list.
+        */
+       kprobe_flush_task(tsk);
+
+       /* Task is done with its stack. */
+       put_task_stack(tsk);
+
        cgroup_free(tsk);
        task_numa_free(tsk);
        security_task_free(tsk);
@@ -424,7 +436,18 @@ void __put_task_struct(struct task_struct *tsk)
        if (!profile_handoff_task(tsk))
                free_task(tsk);
 }
+#ifndef CONFIG_PREEMPT_RT_BASE
 EXPORT_SYMBOL_GPL(__put_task_struct);
+#else
+void __put_task_struct_cb(struct rcu_head *rhp)
+{
+       struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu);
+
+       __put_task_struct(tsk);
+
+}
+EXPORT_SYMBOL_GPL(__put_task_struct_cb);
+#endif
 
 void __init __weak arch_task_cache_init(void) { }
 
@@ -563,7 +586,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #ifdef CONFIG_CC_STACKPROTECTOR
        tsk->stack_canary = get_random_canary();
 #endif
-
+       if (orig->cpus_ptr == &orig->cpus_mask)
+               tsk->cpus_ptr = &tsk->cpus_mask;
        /*
         * One for us, one for whoever does the "release_task()" (usually
         * parent)
@@ -575,6 +599,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
        tsk->splice_pipe = NULL;
        tsk->task_frag.page = NULL;
        tsk->wake_q.next = NULL;
+       tsk->wake_q_sleeper.next = NULL;
 
        account_kernel_stack(tsk, 1);
 
@@ -915,6 +940,19 @@ void __mmdrop(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+/*
+ * RCU callback for delayed mm drop. Not strictly rcu, but we don't
+ * want another facility to make this work.
+ */
+void __mmdrop_delayed(struct rcu_head *rhp)
+{
+       struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
+
+       __mmdrop(mm);
+}
+#endif
+
 static inline void __mmput(struct mm_struct *mm)
 {
        VM_BUG_ON(atomic_read(&mm->mm_users));
@@ -1496,6 +1534,9 @@ static void rt_mutex_init_task(struct task_struct *p)
  */
 static void posix_cpu_timers_init(struct task_struct *tsk)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+       tsk->posix_timer_list = NULL;
+#endif
        tsk->cputime_expires.prof_exp = 0;
        tsk->cputime_expires.virt_exp = 0;
        tsk->cputime_expires.sched_exp = 0;
@@ -1648,6 +1689,7 @@ static __latent_entropy struct task_struct *copy_process(
        spin_lock_init(&p->alloc_lock);
 
        init_sigpending(&p->pending);
+       p->sigqueue_cache = NULL;
 
        p->utime = p->stime = p->gtime = 0;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
diff --git a/kernel/futex.c b/kernel/futex.c
index 046cd780d057..2ba7fb04a107 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -936,7 +936,9 @@ void exit_pi_state_list(struct task_struct *curr)
                if (head->next != next) {
                        /* retain curr->pi_lock for the loop invariant */
                        raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+                       raw_spin_unlock_irq(&curr->pi_lock);
                        spin_unlock(&hb->lock);
+                       raw_spin_lock_irq(&curr->pi_lock);
                        put_pi_state(pi_state);
                        continue;
                }
@@ -1430,6 +1432,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
        struct task_struct *new_owner;
        bool postunlock = false;
        DEFINE_WAKE_Q(wake_q);
+       DEFINE_WAKE_Q(wake_sleeper_q);
        int ret = 0;
 
        new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
@@ -1491,13 +1494,13 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
        pi_state->owner = new_owner;
        raw_spin_unlock(&new_owner->pi_lock);
 
-       postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
-
+       postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q,
+                                            &wake_sleeper_q);
 out_unlock:
        raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
        if (postunlock)
-               rt_mutex_postunlock(&wake_q);
+               rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 
        return ret;
 }
@@ -2104,6 +2107,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
                                requeue_pi_wake_futex(this, &key2, hb2);
                                drop_count++;
                                continue;
+                       } else if (ret == -EAGAIN) {
+                               /*
+                                * Waiter was woken by timeout or
+                                * signal and has set pi_blocked_on to
+                                * PI_WAKEUP_INPROGRESS before we
+                                * tried to enqueue it on the rtmutex.
+                                */
+                               this->pi_state = NULL;
+                               put_pi_state(pi_state);
+                               continue;
                        } else if (ret) {
                                /*
                                 * rt_mutex_start_proxy_lock() detected a
@@ -2642,10 +2655,9 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
        if (abs_time) {
                to = &timeout;
 
-               hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
-                                     CLOCK_REALTIME : CLOCK_MONOTONIC,
-                                     HRTIMER_MODE_ABS);
-               hrtimer_init_sleeper(to, current);
+               hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ?
+                                             CLOCK_REALTIME : CLOCK_MONOTONIC,
+                                             HRTIMER_MODE_ABS, current);
                hrtimer_set_expires_range_ns(&to->timer, *abs_time,
                                             current->timer_slack_ns);
        }
@@ -2744,9 +2756,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 
        if (time) {
                to = &timeout;
-               hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
-                                     HRTIMER_MODE_ABS);
-               hrtimer_init_sleeper(to, current);
+               hrtimer_init_sleeper_on_stack(to, CLOCK_REALTIME,
+                                             HRTIMER_MODE_ABS, current);
                hrtimer_set_expires(&to->timer, *time);
        }
 
@@ -2801,7 +2812,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
                goto no_block;
        }
 
-       rt_mutex_init_waiter(&rt_waiter);
+       rt_mutex_init_waiter(&rt_waiter, false);
 
        /*
         * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
@@ -2816,9 +2827,18 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
         * lock handoff sequence.
         */
        raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+       /*
+        * the migrate_disable() here disables migration in the in_atomic() fast
+        * path which is enabled again in the following spin_unlock(). We have
+        * one migrate_disable() pending in the slow-path which is reversed
+        * after the raw_spin_unlock_irq() where we leave the atomic context.
+        */
+       migrate_disable();
+
        spin_unlock(q.lock_ptr);
        ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
        raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+       migrate_enable();
 
        if (ret) {
                if (ret == 1)
@@ -2965,11 +2985,21 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
                 * observed.
                 */
                raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+               /*
+                * Magic trickery for now to make the RT migrate disable
+                * logic happy. The following spin_unlock() happens with
+                * interrupts disabled so the internal migrate_enable()
+                * won't undo the migrate_disable() which was issued when
+                * locking hb->lock.
+                */
+               migrate_disable();
                spin_unlock(&hb->lock);
 
                /* drops pi_state->pi_mutex.wait_lock */
                ret = wake_futex_pi(uaddr, uval, pi_state);
 
+               migrate_enable();
+
                put_pi_state(pi_state);
 
                /*
@@ -3127,7 +3157,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
        struct hrtimer_sleeper timeout, *to = NULL;
        struct futex_pi_state *pi_state = NULL;
        struct rt_mutex_waiter rt_waiter;
-       struct futex_hash_bucket *hb;
+       struct futex_hash_bucket *hb, *hb2;
        union futex_key key2 = FUTEX_KEY_INIT;
        struct futex_q q = futex_q_init;
        int res, ret;
@@ -3143,10 +3173,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 
        if (abs_time) {
                to = &timeout;
-               hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
-                                     CLOCK_REALTIME : CLOCK_MONOTONIC,
-                                     HRTIMER_MODE_ABS);
-               hrtimer_init_sleeper(to, current);
+               hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ?
+                                             CLOCK_REALTIME : CLOCK_MONOTONIC,
+                                             HRTIMER_MODE_ABS, current);
                hrtimer_set_expires_range_ns(&to->timer, *abs_time,
                                             current->timer_slack_ns);
        }
@@ -3155,7 +3184,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
         * The waiter is allocated on our stack, manipulated by the requeue
         * code while we sleep on uaddr.
         */
-       rt_mutex_init_waiter(&rt_waiter);
+       rt_mutex_init_waiter(&rt_waiter, false);
 
        ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
        if (unlikely(ret != 0))
@@ -3186,20 +3215,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
        /* Queue the futex_q, drop the hb lock, wait for wakeup. */
        futex_wait_queue_me(hb, &q, to);
 
-       spin_lock(&hb->lock);
-       ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
-       spin_unlock(&hb->lock);
-       if (ret)
-               goto out_put_keys;
+       /*
+        * On RT we must avoid races with requeue and trying to block
+        * on two mutexes (hb->lock and uaddr2's rtmutex) by
+        * serializing access to pi_blocked_on with pi_lock.
+        */
+       raw_spin_lock_irq(&current->pi_lock);
+       if (current->pi_blocked_on) {
+               /*
+                * We have been requeued or are in the process of
+                * being requeued.
+                */
+               raw_spin_unlock_irq(&current->pi_lock);
+       } else {
+               /*
+                * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS
+                * prevents a concurrent requeue from moving us to the
+                * uaddr2 rtmutex. After that we can safely acquire
+                * (and possibly block on) hb->lock.
+                */
+               current->pi_blocked_on = PI_WAKEUP_INPROGRESS;
+               raw_spin_unlock_irq(&current->pi_lock);
+
+               spin_lock(&hb->lock);
+
+               /*
+                * Clean up pi_blocked_on. We might leak it otherwise
+                * when we succeeded with the hb->lock in the fast
+                * path.
+                */
+               raw_spin_lock_irq(&current->pi_lock);
+               current->pi_blocked_on = NULL;
+               raw_spin_unlock_irq(&current->pi_lock);
+
+               ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+               spin_unlock(&hb->lock);
+               if (ret)
+                       goto out_put_keys;
+       }
 
        /*
-        * In order for us to be here, we know our q.key == key2, and since
-        * we took the hb->lock above, we also know that futex_requeue() has
-        * completed and we no longer have to concern ourselves with a wakeup
-        * race with the atomic proxy lock acquisition by the requeue code. The
-        * futex_requeue dropped our key1 reference and incremented our key2
-        * reference count.
+        * In order to be here, we have either been requeued, are in
+        * the process of being requeued, or requeue successfully
+        * acquired uaddr2 on our behalf.  If pi_blocked_on was
+        * non-null above, we may be racing with a requeue.  Do not
+        * rely on q->lock_ptr to be hb2->lock until after blocking on
+        * hb->lock or hb2->lock. The futex_requeue dropped our key1
+        * reference and incremented our key2 reference count.
         */
+       hb2 = hash_futex(&key2);
 
        /* Check if the requeue code acquired the second futex for us. */
        if (!q.rt_waiter) {
@@ -3208,7 +3272,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
                 * did a lock-steal - fix up the PI-state in that case.
                 */
                if (q.pi_state && (q.pi_state->owner != current)) {
-                       spin_lock(q.lock_ptr);
+                       spin_lock(&hb2->lock);
+                       BUG_ON(&hb2->lock != q.lock_ptr);
                        ret = fixup_pi_state_owner(uaddr2, &q, current);
                        if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
                                pi_state = q.pi_state;
@@ -3219,7 +3284,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
                         * the requeue_pi() code acquired for us.
                         */
                        put_pi_state(q.pi_state);
-                       spin_unlock(q.lock_ptr);
+                       spin_unlock(&hb2->lock);
                }
        } else {
                struct rt_mutex *pi_mutex;
@@ -3233,7 +3298,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
                pi_mutex = &q.pi_state->pi_mutex;
                ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
 
-               spin_lock(q.lock_ptr);
+               spin_lock(&hb2->lock);
+               BUG_ON(&hb2->lock != q.lock_ptr);
                if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
                        ret = 0;
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 79f987b942b8..d1dbacc29941 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -183,10 +183,16 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 {
        irqreturn_t retval;
        unsigned int flags = 0;
+       struct pt_regs *regs = get_irq_regs();
+       u64 ip = regs ? instruction_pointer(regs) : 0;
 
        retval = __handle_irq_event_percpu(desc, &flags);
 
-       add_interrupt_randomness(desc->irq_data.irq, flags);
+#ifdef CONFIG_PREEMPT_RT_FULL
+       desc->random_ip = ip;
+#else
+       add_interrupt_randomness(desc->irq_data.irq, flags, ip);
+#endif
 
        if (!noirqdebug)
                note_interrupt(desc, retval);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 069311541577..f82dcca81712 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -24,6 +24,7 @@
 #include "internals.h"
 
 #ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
 __read_mostly bool force_irqthreads;
 
 static int __init setup_forced_irqthreads(char *arg)
@@ -32,6 +33,7 @@ static int __init setup_forced_irqthreads(char *arg)
        return 0;
 }
 early_param("threadirqs", setup_forced_irqthreads);
+# endif
 #endif
 
 static void __synchronize_hardirq(struct irq_desc *desc)
@@ -224,7 +226,12 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 
        if (desc->affinity_notify) {
                kref_get(&desc->affinity_notify->kref);
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+               swork_queue(&desc->affinity_notify->swork);
+#else
                schedule_work(&desc->affinity_notify->work);
+#endif
        }
        irqd_set(data, IRQD_AFFINITY_SET);
 
@@ -262,10 +269,8 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 }
 EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
 
-static void irq_affinity_notify(struct work_struct *work)
+static void _irq_affinity_notify(struct irq_affinity_notify *notify)
 {
-       struct irq_affinity_notify *notify =
-               container_of(work, struct irq_affinity_notify, work);
        struct irq_desc *desc = irq_to_desc(notify->irq);
        cpumask_var_t cpumask;
        unsigned long flags;
@@ -287,6 +292,35 @@ static void irq_affinity_notify(struct work_struct *work)
        kref_put(&notify->kref, notify->release);
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void init_helper_thread(void)
+{
+       static int init_sworker_once;
+
+       if (init_sworker_once)
+               return;
+       if (WARN_ON(swork_get()))
+               return;
+       init_sworker_once = 1;
+}
+
+static void irq_affinity_notify(struct swork_event *swork)
+{
+       struct irq_affinity_notify *notify =
+               container_of(swork, struct irq_affinity_notify, swork);
+       _irq_affinity_notify(notify);
+}
+
+#else
+
+static void irq_affinity_notify(struct work_struct *work)
+{
+       struct irq_affinity_notify *notify =
+               container_of(work, struct irq_affinity_notify, work);
+       _irq_affinity_notify(notify);
+}
+#endif
+
 /**
  *     irq_set_affinity_notifier - control notification of IRQ affinity changes
  *     @irq:           Interrupt for which to enable/disable notification
@@ -315,7 +349,12 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
        if (notify) {
                notify->irq = irq;
                kref_init(&notify->kref);
+#ifdef CONFIG_PREEMPT_RT_BASE
+               INIT_SWORK(&notify->swork, irq_affinity_notify);
+               init_helper_thread();
+#else
                INIT_WORK(&notify->work, irq_affinity_notify);
+#endif
        }
 
        raw_spin_lock_irqsave(&desc->lock, flags);
@@ -883,7 +922,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
        local_bh_disable();
        ret = action->thread_fn(action->irq, action->dev_id);
        irq_finalize_oneshot(desc, action);
-       local_bh_enable();
+       /*
+        * Interrupts which have real time requirements can be set up
+        * to avoid softirq processing in the thread handler. This is
+        * safe as these interrupts do not raise soft interrupts.
+        */
+       if (irq_settings_no_softirq_call(desc))
+               _local_bh_enable();
+       else
+               local_bh_enable();
        return ret;
 }
 
@@ -980,6 +1027,12 @@ static int irq_thread(void *data)
                if (action_ret == IRQ_WAKE_THREAD)
                        irq_wake_secondary(desc, action);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+               migrate_disable();
+               add_interrupt_randomness(action->irq, 0,
+                                desc->random_ip ^ (unsigned long) action);
+               migrate_enable();
+#endif
                wake_threads_waitq(desc);
        }
 
@@ -1378,6 +1431,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
                        irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
                }
 
+               if (new->flags & IRQF_NO_SOFTIRQ_CALL)
+                       irq_settings_set_no_softirq_call(desc);
+
                if (irq_settings_can_autoenable(desc)) {
                        irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
                } else {
@@ -2159,7 +2215,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state);
  *     This call sets the internal irqchip state of an interrupt,
  *     depending on the value of @which.
  *
- *     This function should be called with preemption disabled if the
+ *     This function should be called with migration disabled if the
  *     interrupt controller has per-cpu registers.
  */
 int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index e43795cd2ccf..47e2f9e23586 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -17,6 +17,7 @@ enum {
        _IRQ_PER_CPU_DEVID      = IRQ_PER_CPU_DEVID,
        _IRQ_IS_POLLED          = IRQ_IS_POLLED,
        _IRQ_DISABLE_UNLAZY     = IRQ_DISABLE_UNLAZY,
+       _IRQ_NO_SOFTIRQ_CALL    = IRQ_NO_SOFTIRQ_CALL,
        _IRQF_MODIFY_MASK       = IRQF_MODIFY_MASK,
 };
 
@@ -31,6 +32,7 @@ enum {
 #define IRQ_PER_CPU_DEVID      GOT_YOU_MORON
 #define IRQ_IS_POLLED          GOT_YOU_MORON
 #define IRQ_DISABLE_UNLAZY     GOT_YOU_MORON
+#define IRQ_NO_SOFTIRQ_CALL    GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK       GOT_YOU_MORON
 
@@ -41,6 +43,16 @@ irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
        desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK);
 }
 
+static inline bool irq_settings_no_softirq_call(struct irq_desc *desc)
+{
+       return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL;
+}
+
+static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc)
+{
+       desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL;
+}
+
 static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
 {
        return desc->status_use_accessors & _IRQ_PER_CPU;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 987d7bca4864..75347fb1dfea 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -445,6 +445,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true");
 
 static int __init irqfixup_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+       pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n");
+       return 1;
+#endif
        irqfixup = 1;
        printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
        printk(KERN_WARNING "This may impact system performance.\n");
@@ -457,6 +461,10 @@ module_param(irqfixup, int, 0644);
 
 static int __init irqpoll_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+       pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n");
+       return 1;
+#endif
        irqfixup = 2;
        printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
                                "enabled\n");
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index bcf107ce0854..2899ba0d23d1 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/interrupt.h>
 #include <asm/processor.h>
 
 
@@ -65,6 +66,8 @@ void __weak arch_irq_work_raise(void)
  */
 bool irq_work_queue_on(struct irq_work *work, int cpu)
 {
+       struct llist_head *list;
+
        /* All work should have been flushed before going offline */
        WARN_ON_ONCE(cpu_is_offline(cpu));
 
@@ -75,7 +78,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
        if (!irq_work_claim(work))
                return false;
 
-       if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+       if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ))
+               list = &per_cpu(lazy_list, cpu);
+       else
+               list = &per_cpu(raised_list, cpu);
+
+       if (llist_add(&work->llnode, list))
                arch_send_call_function_single_ipi(cpu);
 
        return true;
@@ -86,6 +94,9 @@ EXPORT_SYMBOL_GPL(irq_work_queue_on);
 /* Enqueue the irq work @work on the current CPU */
 bool irq_work_queue(struct irq_work *work)
 {
+       struct llist_head *list;
+       bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL);
+
        /* Only queue if not already pending */
        if (!irq_work_claim(work))
                return false;
@@ -93,13 +104,15 @@ bool irq_work_queue(struct irq_work *work)
        /* Queue the entry and raise the IPI if needed. */
        preempt_disable();
 
-       /* If the work is "lazy", handle it from next tick if any */
-       if (work->flags & IRQ_WORK_LAZY) {
-               if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
-                   tick_nohz_tick_stopped())
-                       arch_irq_work_raise();
-       } else {
-               if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+       lazy_work = work->flags & IRQ_WORK_LAZY;
+
+       if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ)))
+               list = this_cpu_ptr(&lazy_list);
+       else
+               list = this_cpu_ptr(&raised_list);
+
+       if (llist_add(&work->llnode, list)) {
+               if (!lazy_work || tick_nohz_tick_stopped())
                        arch_irq_work_raise();
        }
 
@@ -116,9 +129,8 @@ bool irq_work_needs_cpu(void)
        raised = this_cpu_ptr(&raised_list);
        lazy = this_cpu_ptr(&lazy_list);
 
-       if (llist_empty(raised) || arch_irq_work_has_interrupt())
-               if (llist_empty(lazy))
-                       return false;
+       if (llist_empty(raised) && llist_empty(lazy))
+               return false;
 
        /* All work should have been flushed before going offline */
        WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -132,7 +144,7 @@ static void irq_work_run_list(struct llist_head *list)
        struct irq_work *work;
        struct llist_node *llnode;
 
-       BUG_ON(!irqs_disabled());
+       BUG_ON_NONRT(!irqs_disabled());
 
        if (llist_empty(list))
                return;
@@ -169,7 +181,16 @@ static void irq_work_run_list(struct llist_head *list)
 void irq_work_run(void)
 {
        irq_work_run_list(this_cpu_ptr(&raised_list));
-       irq_work_run_list(this_cpu_ptr(&lazy_list));
+       if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) {
+               /*
+                * NOTE: we raise softirq via IPI for safety,
+                * and execute in irq_work_tick() to move the
+                * overhead from hard to soft irq context.
+                */
+               if (!llist_empty(this_cpu_ptr(&lazy_list)))
+                       raise_softirq(TIMER_SOFTIRQ);
+       } else
+               irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -179,8 +200,17 @@ void irq_work_tick(void)
 
        if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
                irq_work_run_list(raised);
+
+       if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
+               irq_work_run_list(this_cpu_ptr(&lazy_list));
+}
+
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+void irq_work_tick_soft(void)
+{
        irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
+#endif
 
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 46ba853656f6..9a23632b6294 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -140,6 +140,15 @@ KERNEL_ATTR_RO(vmcoreinfo);
 
 #endif /* CONFIG_CRASH_CORE */
 
+#if defined(CONFIG_PREEMPT_RT_FULL)
+static ssize_t realtime_show(struct kobject *kobj,
+                            struct kobj_attribute *attr, char *buf)
+{
+       return sprintf(buf, "%d\n", 1);
+}
+KERNEL_ATTR_RO(realtime);
+#endif
+
 /* whether file capabilities are enabled */
 static ssize_t fscaps_show(struct kobject *kobj,
                                  struct kobj_attribute *attr, char *buf)
@@ -230,6 +239,9 @@ static struct attribute * kernel_attrs[] = {
 #ifndef CONFIG_TINY_RCU
        &rcu_expedited_attr.attr,
        &rcu_normal_attr.attr,
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+       &realtime_attr.attr,
 #endif
        NULL
 };
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 392c7f23af76..c0bf04b6b965 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -3,7 +3,7 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT                := n
 
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+obj-y += semaphore.o percpu-rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@@ -12,7 +12,11 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
 endif
 
+ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
+obj-y += mutex.o
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+endif
+obj-y += rwsem.o
 obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
@@ -25,8 +29,11 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
+endif
+obj-$(CONFIG_PREEMPT_RT_FULL) += mutex-rt.o rwsem-rt.o rwlock-rt.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
 obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index d7c155048ea9..def51a27f20f 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3914,6 +3914,7 @@ static void check_flags(unsigned long flags)
                }
        }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
        /*
         * We dont accurately track softirq state in e.g.
         * hardirq contexts (such as on 4KSTACKS), so only
@@ -3928,6 +3929,7 @@ static void check_flags(unsigned long flags)
                        DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
                }
        }
+#endif
 
        if (!debug_locks)
                print_irqtrace_events(current);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 6dca260eeccf..5d01ac590d4c 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -26,7 +26,6 @@
 #include <linux/kthread.h>
 #include <linux/sched/rt.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/smp.h>
diff --git a/kernel/locking/mutex-rt.c b/kernel/locking/mutex-rt.c
new file mode 100644
index 000000000000..4f81595c0f52
--- /dev/null
+++ b/kernel/locking/mutex-rt.c
@@ -0,0 +1,223 @@
+/*
+ * kernel/rt.c
+ *
+ * Real-Time Preemption Support
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * historic credit for proving that Linux spinlocks can be implemented via
+ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow
+ * and others) who prototyped it on 2.4 and did lots of comparative
+ * research and analysis; TimeSys, for proving that you can implement a
+ * fully preemptible kernel via the use of IRQ threading and mutexes;
+ * Bill Huey for persuasively arguing on lkml that the mutex model is the
+ * right one; and to MontaVista, who ported pmutexes to 2.6.
+ *
+ * This code is a from-scratch implementation and is not based on pmutexes,
+ * but the idea of converting spinlocks to mutexes is used here too.
+ *
+ * lock debugging, locking tree, deadlock detection:
+ *
+ *  Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey
+ *  Released under the General Public License (GPL).
+ *
+ * Includes portions of the generic R/W semaphore implementation from:
+ *
+ *  Copyright (c) 2001   David Howells (dhowells@redhat.com).
+ *  - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ *  - Derived also from comments by Linus
+ *
+ * Pending ownership of locks and ownership stealing:
+ *
+ *  Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt
+ *
+ *   (also by Steven Rostedt)
+ *    - Converted single pi_lock to individual task locks.
+ *
+ * By Esben Nielsen:
+ *    Doing priority inheritance with help of the scheduler.
+ *
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *  - major rework based on Esben Nielsens initial patch
+ *  - replaced thread_info references by task_struct refs
+ *  - removed task->pending_owner dependency
+ *  - BKL drop/reacquire for semaphore style locks to avoid deadlocks
+ *    in the scheduler return path as discussed with Steven Rostedt
+ *
+ *  Copyright (C) 2006, Kihon Technologies Inc.
+ *    Steven Rostedt <rostedt@goodmis.org>
+ *  - debugged and patched Thomas Gleixner's rework.
+ *  - added back the cmpxchg to the rework.
+ *  - turned atomic require back on for SMP.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/syscalls.h>
+#include <linux/interrupt.h>
+#include <linux/plist.h>
+#include <linux/fs.h>
+#include <linux/futex.h>
+#include <linux/hrtimer.h>
+
+#include "rtmutex_common.h"
+
+/*
+ * struct mutex functions
+ */
+void __mutex_do_init(struct mutex *mutex, const char *name,
+                    struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       /*
+        * Make sure we are not reinitializing a held lock:
+        */
+       debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
+       lockdep_init_map(&mutex->dep_map, name, key, 0);
+#endif
+       mutex->lock.save_state = 0;
+}
+EXPORT_SYMBOL(__mutex_do_init);
+
+void __lockfunc _mutex_lock(struct mutex *lock)
+{
+       mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+       __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(_mutex_lock);
+
+void __lockfunc _mutex_lock_io(struct mutex *lock)
+{
+       int token;
+
+       token = io_schedule_prepare();
+       _mutex_lock(lock);
+       io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(_mutex_lock_io);
+
+int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
+{
+       int ret;
+
+       mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+       ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE);
+       if (ret)
+               mutex_release(&lock->dep_map, 1, _RET_IP_);
+       return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_interruptible);
+
+int __lockfunc _mutex_lock_killable(struct mutex *lock)
+{
+       int ret;
+
+       mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+       ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE);
+       if (ret)
+               mutex_release(&lock->dep_map, 1, _RET_IP_);
+       return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_killable);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass)
+{
+       mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+       __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(_mutex_lock_nested);
+
+void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass)
+{
+       int token;
+
+       token = io_schedule_prepare();
+
+       mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+       __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+
+       io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(_mutex_lock_io_nested);
+
+void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
+{
+       mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_);
+       __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(_mutex_lock_nest_lock);
+
+int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass)
+{
+       int ret;
+
+       mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+       ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE);
+       if (ret)
+               mutex_release(&lock->dep_map, 1, _RET_IP_);
+       return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_interruptible_nested);
+
+int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass)
+{
+       int ret;
+
+       mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+       ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE);
+       if (ret)
+               mutex_release(&lock->dep_map, 1, _RET_IP_);
+       return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_killable_nested);
+#endif
+
+int __lockfunc _mutex_trylock(struct mutex *lock)
+{
+       int ret = __rt_mutex_trylock(&lock->lock);
+
+       if (ret)
+               mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+       return ret;
+}
+EXPORT_SYMBOL(_mutex_trylock);
+
+void __lockfunc _mutex_unlock(struct mutex *lock)
+{
+       mutex_release(&lock->dep_map, 1, _RET_IP_);
+       __rt_mutex_unlock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_unlock);
+
+/**
+ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
+ * @cnt: the atomic which we are to dec
+ * @lock: the mutex to return holding if we dec to 0
+ *
+ * return true and hold lock if we dec to 0, return false otherwise
+ */
+int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
+{
+       /* dec if we can't possibly hit 0 */
+       if (atomic_add_unless(cnt, -1, 1))
+               return 0;
+       /* we might hit 0, so take the lock */
+       mutex_lock(lock);
+       if (!atomic_dec_and_test(cnt)) {
+               /* when we actually did the dec, we didn't hit 0 */
+               mutex_unlock(lock);
+               return 0;
+       }
+       /* we hit 0, and we hold the lock */
+       return 1;
+}
+EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4ad35718f123..08e233b7dc21 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -7,6 +7,11 @@
  *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
+ *  Adaptive Spinlocks:
+ *  Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich,
+ *                                  and Peter Morreale,
+ * Adaptive Spinlocks simplification:
+ *  Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com>
  *
  *  See Documentation/locking/rt-mutex-design.txt for details.
  */
@@ -18,6 +23,8 @@
 #include <linux/sched/wake_q.h>
 #include <linux/sched/debug.h>
 #include <linux/timer.h>
+#include <linux/ww_mutex.h>
+#include <linux/blkdev.h>
 
 #include "rtmutex_common.h"
 
@@ -135,6 +142,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
                WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
+static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
+{
+       return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+               waiter != PI_REQUEUE_INPROGRESS;
+}
+
 /*
  * We can speed up the acquire/release, if there's no debugging state to be
  * set up.
@@ -228,7 +241,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
  * Only use with rt_mutex_waiter_{less,equal}()
  */
 #define task_to_waiter(p)      \
-       &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+       &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline, .task = (p) }
 
 static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
@@ -268,6 +281,27 @@ rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
        return 1;
 }
 
+#define STEAL_NORMAL  0
+#define STEAL_LATERAL 1
+
+static inline int
+rt_mutex_steal(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, int mode)
+{
+       struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock);
+
+       if (waiter == top_waiter || rt_mutex_waiter_less(waiter, top_waiter))
+               return 1;
+
+       /*
+        * Note that RT tasks are excluded from lateral-steals
+        * to prevent the introduction of an unbounded latency.
+        */
+       if (mode == STEAL_NORMAL || rt_task(waiter->task))
+               return 0;
+
+       return rt_mutex_waiter_equal(waiter, top_waiter);
+}
+
 static void
 rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 {
@@ -372,6 +406,14 @@ static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
        return debug_rt_mutex_detect_deadlock(waiter, chwalk);
 }
 
+static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
+{
+       if (waiter->savestate)
+               wake_up_lock_sleeper(waiter->task);
+       else
+               wake_up_process(waiter->task);
+}
+
 /*
  * Max number of times we'll walk the boosting chain:
  */
@@ -379,7 +421,8 @@ int max_lock_depth = 1024;
 
 static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
 {
-       return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+       return rt_mutex_real_waiter(p->pi_blocked_on) ?
+               p->pi_blocked_on->lock : NULL;
 }
 
 /*
@@ -515,7 +558,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
         * reached or the state of the chain has changed while we
         * dropped the locks.
         */
-       if (!waiter)
+       if (!rt_mutex_real_waiter(waiter))
                goto out_unlock_pi;
 
        /*
@@ -696,13 +739,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
         * follow here. This is the end of the chain we are walking.
         */
        if (!rt_mutex_owner(lock)) {
+               struct rt_mutex_waiter *lock_top_waiter;
+
                /*
                 * If the requeue [7] above changed the top waiter,
                 * then we need to wake the new top waiter up to try
                 * to get the lock.
                 */
-               if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
-                       wake_up_process(rt_mutex_top_waiter(lock)->task);
+               lock_top_waiter = rt_mutex_top_waiter(lock);
+               if (prerequeue_top_waiter != lock_top_waiter)
+                       rt_mutex_wake_waiter(lock_top_waiter);
                raw_spin_unlock_irq(&lock->wait_lock);
                return 0;
        }
@@ -804,9 +850,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
  * @task:   The task which wants to acquire the lock
  * @waiter: The waiter that is queued to the lock's wait tree if the
  *         callsite called task_blocked_on_lock(), otherwise NULL
+ * @mode:   Lock steal mode (STEAL_NORMAL, STEAL_LATERAL)
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
-                               struct rt_mutex_waiter *waiter)
+static int __try_to_take_rt_mutex(struct rt_mutex *lock,
+                                 struct task_struct *task,
+                                 struct rt_mutex_waiter *waiter, int mode)
 {
        lockdep_assert_held(&lock->wait_lock);
 
@@ -842,12 +890,11 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
         */
        if (waiter) {
                /*
-                * If waiter is not the highest priority waiter of
-                * @lock, give up.
+                * If waiter is not the highest priority waiter of @lock,
+                * or its peer when lateral steal is allowed, give up.
                 */
-               if (waiter != rt_mutex_top_waiter(lock))
+               if (!rt_mutex_steal(lock, waiter, mode))
                        return 0;
-
                /*
                 * We can acquire the lock. Remove the waiter from the
                 * lock waiters tree.
@@ -865,14 +912,12 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
                 */
                if (rt_mutex_has_waiters(lock)) {
                        /*
-                        * If @task->prio is greater than or equal to
-                        * the top waiter priority (kernel view),
-                        * @task lost.
+                        * If @task->prio is greater than the top waiter
+                        * priority (kernel view), or equal to it when a
+                        * lateral steal is forbidden, @task lost.
                         */
-                       if (!rt_mutex_waiter_less(task_to_waiter(task),
-                                                 rt_mutex_top_waiter(lock)))
+                       if (!rt_mutex_steal(lock, task_to_waiter(task), mode))
                                return 0;
-
                        /*
                         * The current top waiter stays enqueued. We
                         * don't have to change anything in the lock
@@ -919,6 +964,351 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
        return 1;
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * preemptible spin_lock functions:
+ */
+static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
+                                        void  (*slowfn)(struct rt_mutex *lock))
+{
+       might_sleep_no_state_check();
+
+       if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+               return;
+       else
+               slowfn(lock);
+}
+
+static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock,
+                                          void  (*slowfn)(struct rt_mutex *lock))
+{
+       if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+               return;
+       else
+               slowfn(lock);
+}
+#ifdef CONFIG_SMP
+/*
+ * Note that owner is a speculative pointer and dereferencing relies
+ * on rcu_read_lock() and the check against the lock owner.
+ */
+static int adaptive_wait(struct rt_mutex *lock,
+                        struct task_struct *owner)
+{
+       int res = 0;
+
+       rcu_read_lock();
+       for (;;) {
+               if (owner != rt_mutex_owner(lock))
+                       break;
+               /*
+                * Ensure that owner->on_cpu is dereferenced _after_
+                * checking the above to be valid.
+                */
+               barrier();
+               if (!owner->on_cpu) {
+                       res = 1;
+                       break;
+               }
+               cpu_relax();
+       }
+       rcu_read_unlock();
+       return res;
+}
+#else
+static int adaptive_wait(struct rt_mutex *lock,
+                        struct task_struct *orig_owner)
+{
+       return 1;
+}
+#endif
+
+static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
+                                  struct rt_mutex_waiter *waiter,
+                                  struct task_struct *task,
+                                  enum rtmutex_chainwalk chwalk);
+/*
+ * Slow path lock function spin_lock style: this variant is very
+ * careful not to miss any non-lock wakeups.
+ *
+ * We store the current state under p->pi_lock in p->saved_state and
+ * the try_to_wake_up() code handles this accordingly.
+ */
+void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock,
+                                         struct rt_mutex_waiter *waiter,
+                                         unsigned long flags)
+{
+       struct task_struct *lock_owner, *self = current;
+       struct rt_mutex_waiter *top_waiter;
+       int ret;
+
+       if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL))
+               return;
+
+       BUG_ON(rt_mutex_owner(lock) == self);
+
+       /*
+        * We save whatever state the task is in and we'll restore it
+        * after acquiring the lock taking real wakeups into account
+        * as well. We are serialized via pi_lock against wakeups. See
+        * try_to_wake_up().
+        */
+       raw_spin_lock(&self->pi_lock);
+       self->saved_state = self->state;
+       __set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+       raw_spin_unlock(&self->pi_lock);
+
+       ret = task_blocks_on_rt_mutex(lock, waiter, self, RT_MUTEX_MIN_CHAINWALK);
+       BUG_ON(ret);
+
+       for (;;) {
+               /* Try to acquire the lock again. */
+               if (__try_to_take_rt_mutex(lock, self, waiter, STEAL_LATERAL))
+                       break;
+
+               top_waiter = rt_mutex_top_waiter(lock);
+               lock_owner = rt_mutex_owner(lock);
+
+               raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+               debug_rt_mutex_print_deadlock(waiter);
+
+               if (top_waiter != waiter || adaptive_wait(lock, lock_owner))
+                       schedule();
+
+               raw_spin_lock_irqsave(&lock->wait_lock, flags);
+
+               raw_spin_lock(&self->pi_lock);
+               __set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+               raw_spin_unlock(&self->pi_lock);
+       }
+
+       /*
+        * Restore the task state to current->saved_state. We set it
+        * to the original state above and the try_to_wake_up() code
+        * has possibly updated it when a real (non-rtmutex) wakeup
+        * happened while we were blocked. Clear saved_state so
+        * try_to_wakeup() does not get confused.
+        */
+       raw_spin_lock(&self->pi_lock);
+       __set_current_state_no_track(self->saved_state);
+       self->saved_state = TASK_RUNNING;
+       raw_spin_unlock(&self->pi_lock);
+
+       /*
+        * try_to_take_rt_mutex() sets the waiter bit
+        * unconditionally. We might have to fix that up:
+        */
+       fixup_rt_mutex_waiters(lock);
+
+       BUG_ON(rt_mutex_has_waiters(lock) && waiter == rt_mutex_top_waiter(lock));
+       BUG_ON(!RB_EMPTY_NODE(&waiter->tree_entry));
+}
+
+static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
+{
+       struct rt_mutex_waiter waiter;
+       unsigned long flags;
+
+       rt_mutex_init_waiter(&waiter, true);
+
+       raw_spin_lock_irqsave(&lock->wait_lock, flags);
+       rt_spin_lock_slowlock_locked(lock, &waiter, flags);
+       raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+       debug_rt_mutex_free_waiter(&waiter);
+}
+
+static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock,
+                                            struct wake_q_head *wake_q,
+                                            struct wake_q_head *wq_sleeper);
+/*
+ * Slow path to release a rt_mutex spin_lock style
+ */
+void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+       unsigned long flags;
+       DEFINE_WAKE_Q(wake_q);
+       DEFINE_WAKE_Q(wake_sleeper_q);
+       bool postunlock;
+
+       raw_spin_lock_irqsave(&lock->wait_lock, flags);
+       postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q);
+       raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+       if (postunlock)
+               rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
+}
+
+void __lockfunc rt_spin_lock(spinlock_t *lock)
+{
+       sleeping_lock_inc();
+       migrate_disable();
+       spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+       rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+}
+EXPORT_SYMBOL(rt_spin_lock);
+
+void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
+{
+       rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+       sleeping_lock_inc();
+       migrate_disable();
+       spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+       rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+}
+EXPORT_SYMBOL(rt_spin_lock_nested);
+#endif
+
+void __lockfunc rt_spin_unlock(spinlock_t *lock)
+{
+       /* NOTE: we always pass in '1' for nested, for simplicity */
+       spin_release(&lock->dep_map, 1, _RET_IP_);
+       rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+       migrate_enable();
+       sleeping_lock_dec();
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
+{
+       rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(__rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), we lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
+{
+       spin_lock(lock);
+       spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_unlock_wait);
+
+int __lockfunc rt_spin_trylock(spinlock_t *lock)
+{
+       int ret;
+
+       sleeping_lock_inc();
+       migrate_disable();
+       ret = __rt_mutex_trylock(&lock->lock);
+       if (ret) {
+               spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+       } else {
+               migrate_enable();
+               sleeping_lock_dec();
+       }
+       return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock);
+
+int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
+{
+       int ret;
+
+       local_bh_disable();
+       ret = __rt_mutex_trylock(&lock->lock);
+       if (ret) {
+               sleeping_lock_inc();
+               migrate_disable();
+               spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+       } else
+               local_bh_enable();
+       return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_bh);
+
+int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
+{
+       int ret;
+
+       *flags = 0;
+       ret = __rt_mutex_trylock(&lock->lock);
+       if (ret) {
+               sleeping_lock_inc();
+               migrate_disable();
+               spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+       }
+       return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_irqsave);
+
+int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
+{
+       /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+       if (atomic_add_unless(atomic, -1, 1))
+               return 0;
+       rt_spin_lock(lock);
+       if (atomic_dec_and_test(atomic))
+               return 1;
+       rt_spin_unlock(lock);
+       return 0;
+}
+EXPORT_SYMBOL(atomic_dec_and_spin_lock);
+
+void
+__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       /*
+        * Make sure we are not reinitializing a held lock:
+        */
+       debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+       lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+
+#endif /* PREEMPT_RT_FULL */
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+       static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+       struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+       struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx);
+
+       if (!hold_ctx)
+               return 0;
+
+       if (unlikely(ctx == hold_ctx))
+               return -EALREADY;
+
+       if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
+           (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+#ifdef CONFIG_DEBUG_MUTEXES
+               DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+               ctx->contending_lock = ww;
+#endif
+               return -EDEADLK;
+       }
+
+       return 0;
+}
+#else
+       static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+       BUG();
+       return 0;
+}
+
+#endif
+
+static inline int
+try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+                    struct rt_mutex_waiter *waiter)
+{
+       return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
+}
+
 /*
  * Task blocks on lock.
  *
@@ -951,6 +1341,22 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
                return -EDEADLK;
 
        raw_spin_lock(&task->pi_lock);
+       /*
+        * In the case of futex requeue PI, this will be a proxy
+        * lock. The task will wake unaware that it is enqueueed on
+        * this lock. Avoid blocking on two locks and corrupting
+        * pi_blocked_on via the PI_WAKEUP_INPROGRESS
+        * flag. futex_wait_requeue_pi() sets this when it wakes up
+        * before requeue (due to a signal or timeout). Do not enqueue
+        * the task if PI_WAKEUP_INPROGRESS is set.
+        */
+       if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
+               raw_spin_unlock(&task->pi_lock);
+               return -EAGAIN;
+       }
+
+       BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on));
+
        waiter->task = task;
        waiter->lock = lock;
        waiter->prio = task->prio;
@@ -974,7 +1380,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
                rt_mutex_enqueue_pi(owner, waiter);
 
                rt_mutex_adjust_prio(owner);
-               if (owner->pi_blocked_on)
+               if (rt_mutex_real_waiter(owner->pi_blocked_on))
                        chain_walk = 1;
        } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
                chain_walk = 1;
@@ -1016,6 +1422,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  * Called with lock->wait_lock held and interrupts disabled.
  */
 static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
+                                   struct wake_q_head *wake_sleeper_q,
                                    struct rt_mutex *lock)
 {
        struct rt_mutex_waiter *waiter;
@@ -1055,7 +1462,10 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
         * Pairs with preempt_enable() in rt_mutex_postunlock();
         */
        preempt_disable();
-       wake_q_add(wake_q, waiter->task);
+       if (waiter->savestate)
+               wake_q_add_sleeper(wake_sleeper_q, waiter->task);
+       else
+               wake_q_add(wake_q, waiter->task);
        raw_spin_unlock(&current->pi_lock);
 }
 
@@ -1070,7 +1480,7 @@ static void remove_waiter(struct rt_mutex *lock,
 {
        bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
        struct task_struct *owner = rt_mutex_owner(lock);
-       struct rt_mutex *next_lock;
+       struct rt_mutex *next_lock = NULL;
 
        lockdep_assert_held(&lock->wait_lock);
 
@@ -1096,7 +1506,8 @@ static void remove_waiter(struct rt_mutex *lock,
        rt_mutex_adjust_prio(owner);
 
        /* Store the lock on which owner is blocked or NULL */
-       next_lock = task_blocked_on_lock(owner);
+       if (rt_mutex_real_waiter(owner->pi_blocked_on))
+               next_lock = task_blocked_on_lock(owner);
 
        raw_spin_unlock(&owner->pi_lock);
 
@@ -1132,26 +1543,28 @@ void rt_mutex_adjust_pi(struct task_struct *task)
        raw_spin_lock_irqsave(&task->pi_lock, flags);
 
        waiter = task->pi_blocked_on;
-       if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+       if (!rt_mutex_real_waiter(waiter) ||
+           rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
                raw_spin_unlock_irqrestore(&task->pi_lock, flags);
                return;
        }
        next_lock = waiter->lock;
-       raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
        /* gets dropped in rt_mutex_adjust_prio_chain()! */
        get_task_struct(task);
 
+       raw_spin_unlock_irqrestore(&task->pi_lock, flags);
        rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
                                   next_lock, NULL, task);
 }
 
-void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate)
 {
        debug_rt_mutex_init_waiter(waiter);
        RB_CLEAR_NODE(&waiter->pi_tree_entry);
        RB_CLEAR_NODE(&waiter->tree_entry);
        waiter->task = NULL;
+       waiter->savestate = savestate;
 }
 
 /**
@@ -1167,7 +1580,8 @@ void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
                    struct hrtimer_sleeper *timeout,
-                   struct rt_mutex_waiter *waiter)
+                   struct rt_mutex_waiter *waiter,
+                   struct ww_acquire_ctx *ww_ctx)
 {
        int ret = 0;
 
@@ -1176,16 +1590,17 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
                if (try_to_take_rt_mutex(lock, current, waiter))
                        break;
 
-               /*
-                * TASK_INTERRUPTIBLE checks for signals and
-                * timeout. Ignored otherwise.
-                */
-               if (likely(state == TASK_INTERRUPTIBLE)) {
-                       /* Signal pending? */
-                       if (signal_pending(current))
-                               ret = -EINTR;
-                       if (timeout && !timeout->task)
-                               ret = -ETIMEDOUT;
+               if (timeout && !timeout->task) {
+                       ret = -ETIMEDOUT;
+                       break;
+               }
+               if (signal_pending_state(state, current)) {
+                       ret = -EINTR;
+                       break;
+               }
+
+               if (ww_ctx && ww_ctx->acquired > 0) {
+                       ret = __mutex_lock_check_stamp(lock, ww_ctx);
                        if (ret)
                                break;
                }
@@ -1224,33 +1639,104 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
        }
 }
 
-/*
- * Slow path lock function:
- */
-static int __sched
-rt_mutex_slowlock(struct rt_mutex *lock, int state,
-                 struct hrtimer_sleeper *timeout,
-                 enum rtmutex_chainwalk chwalk)
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+                                                  struct ww_acquire_ctx *ww_ctx)
 {
-       struct rt_mutex_waiter waiter;
-       unsigned long flags;
-       int ret = 0;
+#ifdef CONFIG_DEBUG_MUTEXES
+       /*
+        * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+        * but released with a normal mutex_unlock in this call.
+        *
+        * This should never happen, always use ww_mutex_unlock.
+        */
+       DEBUG_LOCKS_WARN_ON(ww->ctx);
 
-       rt_mutex_init_waiter(&waiter);
+       /*
+        * Not quite done after calling ww_acquire_done() ?
+        */
+       DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+       if (ww_ctx->contending_lock) {
+               /*
+                * After -EDEADLK you tried to
+                * acquire a different ww_mutex? Bad!
+                */
+               DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+               /*
+                * You called ww_mutex_lock after receiving -EDEADLK,
+                * but 'forgot' to unlock everything else first?
+                */
+               DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+               ww_ctx->contending_lock = NULL;
+       }
 
        /*
-        * Technically we could use raw_spin_[un]lock_irq() here, but this can
-        * be called in early boot if the cmpxchg() fast path is disabled
-        * (debug, no architecture support). In this case we will acquire the
-        * rtmutex with lock->wait_lock held. But we cannot unconditionally
-        * enable interrupts in that early boot case. So we need to use the
-        * irqsave/restore variants.
+        * Naughty, using a different class will lead to undefined behavior!
         */
-       raw_spin_lock_irqsave(&lock->wait_lock, flags);
+       DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+       ww_ctx->acquired++;
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+                                 struct ww_acquire_ctx *ww_ctx)
+{
+       struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+       struct rt_mutex_waiter *waiter, *n;
+
+       /*
+        * This branch gets optimized out for the common case,
+        * and is only important for ww_mutex_lock.
+        */
+       ww_mutex_lock_acquired(ww, ww_ctx);
+       ww->ctx = ww_ctx;
+
+       /*
+        * Give any possible sleeping processes the chance to wake up,
+        * so they can recheck if they have to back off.
+        */
+       rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters.rb_root,
+                                            tree_entry) {
+               /* XXX debug rt mutex waiter wakeup */
+
+               BUG_ON(waiter->lock != lock);
+               rt_mutex_wake_waiter(waiter);
+       }
+}
+
+#else
+
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+                                 struct ww_acquire_ctx *ww_ctx)
+{
+       BUG();
+}
+#endif
+
+int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state,
+                                    struct hrtimer_sleeper *timeout,
+                                    enum rtmutex_chainwalk chwalk,
+                                    struct ww_acquire_ctx *ww_ctx,
+                                    struct rt_mutex_waiter *waiter)
+{
+       int ret;
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (ww_ctx) {
+               struct ww_mutex *ww;
+
+               ww = container_of(lock, struct ww_mutex, base.lock);
+               if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+                       return -EALREADY;
+       }
+#endif
 
        /* Try to acquire the lock again: */
        if (try_to_take_rt_mutex(lock, current, NULL)) {
-               raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+               if (ww_ctx)
+                       ww_mutex_account_lock(lock, ww_ctx);
                return 0;
        }
 
@@ -1260,17 +1746,27 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
        if (unlikely(timeout))
                hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
 
-       ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
+       ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk);
 
-       if (likely(!ret))
+       if (likely(!ret)) {
                /* sleep on the mutex */
-               ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
+               ret = __rt_mutex_slowlock(lock, state, timeout, waiter,
+                                         ww_ctx);
+       } else if (ww_ctx) {
+               /* ww_mutex received EDEADLK, let it become EALREADY */
+               ret = __mutex_lock_check_stamp(lock, ww_ctx);
+               BUG_ON(!ret);
+       }
 
        if (unlikely(ret)) {
                __set_current_state(TASK_RUNNING);
                if (rt_mutex_has_waiters(lock))
-                       remove_waiter(lock, &waiter);
-               rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+                       remove_waiter(lock, waiter);
+               /* ww_mutex want to report EDEADLK/EALREADY, let them */
+               if (!ww_ctx)
+                       rt_mutex_handle_deadlock(ret, chwalk, waiter);
+       } else if (ww_ctx) {
+               ww_mutex_account_lock(lock, ww_ctx);
        }
 
        /*
@@ -1278,6 +1774,36 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
         * unconditionally. We might have to fix that up.
         */
        fixup_rt_mutex_waiters(lock);
+       return ret;
+}
+
+/*
+ * Slow path lock function:
+ */
+static int __sched
+rt_mutex_slowlock(struct rt_mutex *lock, int state,
+                 struct hrtimer_sleeper *timeout,
+                 enum rtmutex_chainwalk chwalk,
+                 struct ww_acquire_ctx *ww_ctx)
+{
+       struct rt_mutex_waiter waiter;
+       unsigned long flags;
+       int ret = 0;
+
+       rt_mutex_init_waiter(&waiter, false);
+
+       /*
+        * Technically we could use raw_spin_[un]lock_irq() here, but this can
+        * be called in early boot if the cmpxchg() fast path is disabled
+        * (debug, no architecture support). In this case we will acquire the
+        * rtmutex with lock->wait_lock held. But we cannot unconditionally
+        * enable interrupts in that early boot case. So we need to use the
+        * irqsave/restore variants.
+        */
+       raw_spin_lock_irqsave(&lock->wait_lock, flags);
+
+       ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx,
+                                      &waiter);
 
        raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
@@ -1338,7 +1864,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
  * Return whether the current task needs to call rt_mutex_postunlock().
  */
 static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
-                                       struct wake_q_head *wake_q)
+                                       struct wake_q_head *wake_q,
+                                       struct wake_q_head *wake_sleeper_q)
 {
        unsigned long flags;
 
@@ -1392,7 +1919,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
         *
         * Queue the next waiter for wakeup once we release the wait_lock.
         */
-       mark_wakeup_next_waiter(wake_q, lock);
+       mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock);
        raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
        return true; /* call rt_mutex_postunlock() */
@@ -1406,29 +1933,45 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
  */
 static inline int
 rt_mutex_fastlock(struct rt_mutex *lock, int state,
+                 struct ww_acquire_ctx *ww_ctx,
                  int (*slowfn)(struct rt_mutex *lock, int state,
                                struct hrtimer_sleeper *timeout,
-                               enum rtmutex_chainwalk chwalk))
+                               enum rtmutex_chainwalk chwalk,
+                               struct ww_acquire_ctx *ww_ctx))
 {
        if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
                return 0;
 
-       return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+       /*
+        * If rt_mutex blocks, the function sched_submit_work will not call
+        * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true).
+        * We must call blk_schedule_flush_plug here, if we don't call it,
+        * a deadlock in device mapper may happen.
+        */
+       if (unlikely(blk_needs_flush_plug(current)))
+               blk_schedule_flush_plug(current);
+
+       return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx);
 }
 
 static inline int
 rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
                        struct hrtimer_sleeper *timeout,
                        enum rtmutex_chainwalk chwalk,
+                       struct ww_acquire_ctx *ww_ctx,
                        int (*slowfn)(struct rt_mutex *lock, int state,
                                      struct hrtimer_sleeper *timeout,
-                                     enum rtmutex_chainwalk chwalk))
+                                     enum rtmutex_chainwalk chwalk,
+                                     struct ww_acquire_ctx *ww_ctx))
 {
        if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
            likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
                return 0;
 
-       return slowfn(lock, state, timeout, chwalk);
+       if (unlikely(blk_needs_flush_plug(current)))
+               blk_schedule_flush_plug(current);
+
+       return slowfn(lock, state, timeout, chwalk, ww_ctx);
 }
 
 static inline int
@@ -1444,9 +1987,11 @@ rt_mutex_fasttrylock(struct rt_mutex *lock,
 /*
  * Performs the wakeup of the the top-waiter and re-enables preemption.
  */
-void rt_mutex_postunlock(struct wake_q_head *wake_q)
+void rt_mutex_postunlock(struct wake_q_head *wake_q,
+                        struct wake_q_head *wake_sleeper_q)
 {
        wake_up_q(wake_q);
+       wake_up_q_sleeper(wake_sleeper_q);
 
        /* Pairs with preempt_disable() in rt_mutex_slowunlock() */
        preempt_enable();
@@ -1455,23 +2000,40 @@ void rt_mutex_postunlock(struct wake_q_head *wake_q)
 static inline void
 rt_mutex_fastunlock(struct rt_mutex *lock,
                    bool (*slowfn)(struct rt_mutex *lock,
-                                  struct wake_q_head *wqh))
+                                  struct wake_q_head *wqh,
+                                  struct wake_q_head *wq_sleeper))
 {
        DEFINE_WAKE_Q(wake_q);
+       DEFINE_WAKE_Q(wake_sleeper_q);
 
        if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
                return;
 
-       if (slowfn(lock, &wake_q))
-               rt_mutex_postunlock(&wake_q);
+       if (slowfn(lock, &wake_q, &wake_sleeper_q))
+               rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 }
 
-static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
+int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state)
 {
        might_sleep();
+       return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock);
+}
+
+/**
+ * rt_mutex_lock_state - lock a rt_mutex with a given state
+ *
+ * @lock:      The rt_mutex to be locked
+ * @state:     The state to set when blocking on the rt_mutex
+ */
+static int __sched rt_mutex_lock_state(struct rt_mutex *lock, int state, unsigned int subclass)
+{
+       int ret;
 
        mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-       rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+       ret = __rt_mutex_lock_state(lock, state);
+       if (ret)
+               mutex_release(&lock->dep_map, 1, _RET_IP_);
+       return ret;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -1483,7 +2045,7 @@ static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
  */
 void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
 {
-       __rt_mutex_lock(lock, subclass);
+       rt_mutex_lock_state(lock, TASK_UNINTERRUPTIBLE, subclass);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
 #endif
@@ -1496,7 +2058,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
  */
 void __sched rt_mutex_lock(struct rt_mutex *lock)
 {
-       __rt_mutex_lock(lock, 0);
+       rt_mutex_lock_state(lock, TASK_UNINTERRUPTIBLE,  0);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
 #endif
@@ -1512,16 +2074,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock);
  */
 int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 {
-       int ret;
-
-       might_sleep();
-
-       mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-       ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
-       if (ret)
-               mutex_release(&lock->dep_map, 1, _RET_IP_);
-
-       return ret;
+       return rt_mutex_lock_state(lock, TASK_INTERRUPTIBLE, 0);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
@@ -1538,6 +2091,22 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
        return __rt_mutex_slowtrylock(lock);
 }
 
+/**
+ * rt_mutex_lock_killable - lock a rt_mutex killable
+ *
+ * @lock:              the rt_mutex to be locked
+ * @detect_deadlock:   deadlock detection on/off
+ *
+ * Returns:
+ *  0          on success
+ * -EINTR      when interrupted by a signal
+ */
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
+{
+       return rt_mutex_lock_state(lock, TASK_KILLABLE, 0);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
+
 /**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *                     the timeout structure is provided
@@ -1561,6 +2130,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
        mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
        ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
                                       RT_MUTEX_MIN_CHAINWALK,
+                                      NULL,
                                       rt_mutex_slowlock);
        if (ret)
                mutex_release(&lock->dep_map, 1, _RET_IP_);
@@ -1569,6 +2139,18 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 }
 EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
 
+int __sched __rt_mutex_trylock(struct rt_mutex *lock)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (WARN_ON_ONCE(in_irq() || in_nmi()))
+#else
+       if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
+#endif
+               return 0;
+
+       return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
+}
+
 /**
  * rt_mutex_trylock - try to lock a rt_mutex
  *
@@ -1584,10 +2166,7 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock)
 {
        int ret;
 
-       if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
-               return 0;
-
-       ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
+       ret = __rt_mutex_trylock(lock);
        if (ret)
                mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 
@@ -1595,6 +2174,11 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock)
 }
 EXPORT_SYMBOL_GPL(rt_mutex_trylock);
 
+void __sched __rt_mutex_unlock(struct rt_mutex *lock)
+{
+       rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
+}
+
 /**
  * rt_mutex_unlock - unlock a rt_mutex
  *
@@ -1603,16 +2187,13 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock);
 void __sched rt_mutex_unlock(struct rt_mutex *lock)
 {
        mutex_release(&lock->dep_map, 1, _RET_IP_);
-       rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
+       __rt_mutex_unlock(lock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
-/**
- * Futex variant, that since futex variants do not use the fast-path, can be
- * simple and will not need to retry.
- */
-bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
-                                   struct wake_q_head *wake_q)
+static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock,
+                                            struct wake_q_head *wake_q,
+                                            struct wake_q_head *wq_sleeper)
 {
        lockdep_assert_held(&lock->wait_lock);
 
@@ -1629,22 +2210,35 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
         * avoid inversion prior to the wakeup.  preempt_disable()
         * therein pairs with rt_mutex_postunlock().
         */
-       mark_wakeup_next_waiter(wake_q, lock);
+       mark_wakeup_next_waiter(wake_q, wq_sleeper, lock);
 
        return true; /* call postunlock() */
 }
 
+/**
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
+ */
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+                                   struct wake_q_head *wake_q,
+                                   struct wake_q_head *wq_sleeper)
+{
+       return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper);
+}
+
 void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
 {
        DEFINE_WAKE_Q(wake_q);
+       DEFINE_WAKE_Q(wake_sleeper_q);
+       unsigned long flags;
        bool postunlock;
 
-       raw_spin_lock_irq(&lock->wait_lock);
-       postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
-       raw_spin_unlock_irq(&lock->wait_lock);
+       raw_spin_lock_irqsave(&lock->wait_lock, flags);
+       postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q);
+       raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
        if (postunlock)
-               rt_mutex_postunlock(&wake_q);
+               rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 }
 
 /**
@@ -1683,7 +2277,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name,
        if (name && key)
                debug_rt_mutex_init(lock, name, key);
 }
-EXPORT_SYMBOL_GPL(__rt_mutex_init);
+EXPORT_SYMBOL(__rt_mutex_init);
 
 /**
  * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
@@ -1703,6 +2297,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
                                struct task_struct *proxy_owner)
 {
        __rt_mutex_init(lock, NULL, NULL);
+#ifdef CONFIG_DEBUG_SPINLOCK
+       /*
+        * get another key class for the wait_lock. LOCK_PI and UNLOCK_PI is
+        * holding the ->wait_lock of the proxy_lock while unlocking a sleeping
+        * lock.
+        */
+       raw_spin_lock_init(&lock->wait_lock);
+#endif
        debug_rt_mutex_proxy_lock(lock, proxy_owner);
        rt_mutex_set_owner(lock, proxy_owner);
 }
@@ -1735,6 +2337,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
        if (try_to_take_rt_mutex(lock, task, NULL))
                return 1;
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+       /*
+        * In PREEMPT_RT there's an added race.
+        * If the task, that we are about to requeue, times out,
+        * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+        * to skip this task. But right after the task sets
+        * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+        * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+        * This will replace the PI_WAKEUP_INPROGRESS with the actual
+        * lock that it blocks on. We *must not* place this task
+        * on this proxy lock in that case.
+        *
+        * To prevent this race, we first take the task's pi_lock
+        * and check if it has updated its pi_blocked_on. If it has,
+        * we assume that it woke up and we return -EAGAIN.
+        * Otherwise, we set the task's pi_blocked_on to
+        * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+        * it will know that we are in the process of requeuing it.
+        */
+       raw_spin_lock(&task->pi_lock);
+       if (task->pi_blocked_on) {
+               raw_spin_unlock(&task->pi_lock);
+               return -EAGAIN;
+       }
+       task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+       raw_spin_unlock(&task->pi_lock);
+#endif
+
        /* We enforce deadlock detection for futexes */
        ret = task_blocks_on_rt_mutex(lock, waiter, task,
                                      RT_MUTEX_FULL_CHAINWALK);
@@ -1749,7 +2379,7 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
                ret = 0;
        }
 
-       if (unlikely(ret))
+       if (ret && rt_mutex_has_waiters(lock))
                remove_waiter(lock, waiter);
 
        debug_rt_mutex_print_deadlock(waiter);
@@ -1824,17 +2454,36 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
                               struct hrtimer_sleeper *to,
                               struct rt_mutex_waiter *waiter)
 {
+       struct task_struct *tsk = current;
        int ret;
 
        raw_spin_lock_irq(&lock->wait_lock);
        /* sleep on the mutex */
        set_current_state(TASK_INTERRUPTIBLE);
-       ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+       ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL);
        /*
         * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
         * have to fix that up.
         */
        fixup_rt_mutex_waiters(lock);
+       /*
+        * RT has a problem here when the wait got interrupted by a timeout
+        * or a signal. task->pi_blocked_on is still set. The task must
+        * acquire the hash bucket lock when returning from this function.
+        *
+        * If the hash bucket lock is contended then the
+        * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in
+        * task_blocks_on_rt_mutex() will trigger. This can be avoided by
+        * clearing task->pi_blocked_on which removes the task from the
+        * boosting chain of the rtmutex. That's correct because the task
+        * is not longer blocked on it.
+        */
+       if (ret) {
+               raw_spin_lock(&tsk->pi_lock);
+               tsk->pi_blocked_on = NULL;
+               raw_spin_unlock(&tsk->pi_lock);
+       }
+
        raw_spin_unlock_irq(&lock->wait_lock);
 
        return ret;
@@ -1895,3 +2544,99 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 
        return cleanup;
 }
+
+static inline int
+ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+       unsigned tmp;
+
+       if (ctx->deadlock_inject_countdown-- == 0) {
+               tmp = ctx->deadlock_inject_interval;
+               if (tmp > UINT_MAX/4)
+                       tmp = UINT_MAX;
+               else
+                       tmp = tmp*2 + tmp + tmp/2;
+
+               ctx->deadlock_inject_interval = tmp;
+               ctx->deadlock_inject_countdown = tmp;
+               ctx->contending_lock = lock;
+
+               ww_mutex_unlock(lock);
+
+               return -EDEADLK;
+       }
+#endif
+
+       return 0;
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+int __sched
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+       int ret;
+
+       might_sleep();
+
+       mutex_acquire_nest(&lock->base.dep_map, 0, 0,
+                          ctx ? &ctx->dep_map : NULL, _RET_IP_);
+       ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0,
+                               ctx);
+       if (ret)
+               mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+       else if (!ret && ctx && ctx->acquired > 1)
+               return ww_mutex_deadlock_injection(lock, ctx);
+
+       return ret;
+}
+EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
+
+int __sched
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+       int ret;
+
+       might_sleep();
+
+       mutex_acquire_nest(&lock->base.dep_map, 0, 0,
+                          ctx ? &ctx->dep_map : NULL, _RET_IP_);
+       ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0,
+                               ctx);
+       if (ret)
+               mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+       else if (!ret && ctx && ctx->acquired > 1)
+               return ww_mutex_deadlock_injection(lock, ctx);
+
+       return ret;
+}
+EXPORT_SYMBOL_GPL(ww_mutex_lock);
+
+void __sched ww_mutex_unlock(struct ww_mutex *lock)
+{
+       int nest = !!lock->ctx;
+
+       /*
+        * The unlocking fastpath is the 0->1 transition from 'locked'
+        * into 'unlocked' state:
+        */
+       if (nest) {
+#ifdef CONFIG_DEBUG_MUTEXES
+               DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
+#endif
+               if (lock->ctx->acquired > 0)
+                       lock->ctx->acquired--;
+               lock->ctx = NULL;
+       }
+
+       mutex_release(&lock->base.dep_map, nest, _RET_IP_);
+       __rt_mutex_unlock(&lock->base.lock);
+}
+EXPORT_SYMBOL(ww_mutex_unlock);
+
+int __rt_mutex_owner_current(struct rt_mutex *lock)
+{
+       return rt_mutex_owner(lock) == current;
+}
+EXPORT_SYMBOL(__rt_mutex_owner_current);
+#endif
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 68686b3ec3c1..2a157c78e18c 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -15,6 +15,7 @@
 
 #include <linux/rtmutex.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/debug.h>
 
 /*
  * This is the control structure for tasks blocked on a rt_mutex,
@@ -29,6 +30,7 @@ struct rt_mutex_waiter {
        struct rb_node          pi_tree_entry;
        struct task_struct      *task;
        struct rt_mutex         *lock;
+       bool                    savestate;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
        unsigned long           ip;
        struct pid              *deadlock_task_pid;
@@ -129,12 +131,15 @@ enum rtmutex_chainwalk {
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
+#define PI_WAKEUP_INPROGRESS   ((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS  ((struct rt_mutex_waiter *) 2)
+
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
                                       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
                                  struct task_struct *proxy_owner);
-extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
+extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate);
 extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
                                     struct rt_mutex_waiter *waiter,
                                     struct task_struct *task);
@@ -152,9 +157,27 @@ extern int __rt_mutex_futex_trylock(struct rt_mutex *l);
 
 extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
 extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
-                                struct wake_q_head *wqh);
-
-extern void rt_mutex_postunlock(struct wake_q_head *wake_q);
+                                struct wake_q_head *wqh,
+                                struct wake_q_head *wq_sleeper);
+
+extern void rt_mutex_postunlock(struct wake_q_head *wake_q,
+                               struct wake_q_head *wake_sleeper_q);
+
+/* RW semaphore special interface */
+struct ww_acquire_ctx;
+
+extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state);
+extern int __rt_mutex_trylock(struct rt_mutex *lock);
+extern void __rt_mutex_unlock(struct rt_mutex *lock);
+int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state,
+                                    struct hrtimer_sleeper *timeout,
+                                    enum rtmutex_chainwalk chwalk,
+                                    struct ww_acquire_ctx *ww_ctx,
+                                    struct rt_mutex_waiter *waiter);
+void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock,
+                                         struct rt_mutex_waiter *waiter,
+                                         unsigned long flags);
+void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c
new file mode 100644
index 000000000000..f2e155b2c4a8
--- /dev/null
+++ b/kernel/locking/rwlock-rt.c
@@ -0,0 +1,378 @@
+/*
+ */
+#include <linux/sched/debug.h>
+#include <linux/export.h>
+
+#include "rtmutex_common.h"
+#include <linux/rwlock_types_rt.h>
+
+/*
+ * RT-specific reader/writer locks
+ *
+ * write_lock()
+ *  1) Lock lock->rtmutex
+ *  2) Remove the reader BIAS to force readers into the slow path
+ *  3) Wait until all readers have left the critical region
+ *  4) Mark it write locked
+ *
+ * write_unlock()
+ *  1) Remove the write locked marker
+ *  2) Set the reader BIAS so readers can use the fast path again
+ *  3) Unlock lock->rtmutex to release blocked readers
+ *
+ * read_lock()
+ *  1) Try fast path acquisition (reader BIAS is set)
+ *  2) Take lock->rtmutex.wait_lock which protects the writelocked flag
+ *  3) If !writelocked, acquire it for read
+ *  4) If writelocked, block on lock->rtmutex
+ *  5) unlock lock->rtmutex, goto 1)
+ *
+ * read_unlock()
+ *  1) Try fast path release (reader count != 1)
+ *  2) Wake the writer waiting in write_lock()#3
+ *
+ * read_lock()#3 has the consequence, that rw locks on RT are not writer
+ * fair, but writers, which should be avoided in RT tasks (think tasklist
+ * lock), are subject to the rtmutex priority/DL inheritance mechanism.
+ *
+ * It's possible to make the rw locks writer fair by keeping a list of
+ * active readers. A blocked writer would force all newly incoming readers
+ * to block on the rtmutex, but the rtmutex would have to be proxy locked
+ * for one reader after the other. We can't use multi-reader inheritance
+ * because there is no way to support that with
+ * SCHED_DEADLINE. Implementing the one by one reader boosting/handover
+ * mechanism is a major surgery for a very dubious value.
+ *
+ * The risk of writer starvation is there, but the pathological use cases
+ * which trigger it are not necessarily the typical RT workloads.
+ */
+
+void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name,
+                            struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       /*
+        * Make sure we are not reinitializing a held semaphore:
+        */
+       debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+       lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+       atomic_set(&lock->readers, READER_BIAS);
+       rt_mutex_init(&lock->rtmutex);
+       lock->rtmutex.save_state = 1;
+}
+
+int __read_rt_trylock(struct rt_rw_lock *lock)
+{
+       int r, old;
+
+       /*
+        * Increment reader count, if lock->readers < 0, i.e. READER_BIAS is
+        * set.
+        */
+       for (r = atomic_read(&lock->readers); r < 0;) {
+               old = atomic_cmpxchg(&lock->readers, r, r + 1);
+               if (likely(old == r))
+                       return 1;
+               r = old;
+       }
+       return 0;
+}
+
+void __sched __read_rt_lock(struct rt_rw_lock *lock)
+{
+       struct rt_mutex *m = &lock->rtmutex;
+       struct rt_mutex_waiter waiter;
+       unsigned long flags;
+
+       if (__read_rt_trylock(lock))
+               return;
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+       /*
+        * Allow readers as long as the writer has not completely
+        * acquired the semaphore for write.
+        */
+       if (atomic_read(&lock->readers) != WRITER_BIAS) {
+               atomic_inc(&lock->readers);
+               raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+               return;
+       }
+
+       /*
+        * Call into the slow lock path with the rtmutex->wait_lock
+        * held, so this can't result in the following race:
+        *
+        * Reader1              Reader2         Writer
+        *                      read_lock()
+        *                                      write_lock()
+        *                                      rtmutex_lock(m)
+        *                                      swait()
+        * read_lock()
+        * unlock(m->wait_lock)
+        *                      read_unlock()
+        *                      swake()
+        *                                      lock(m->wait_lock)
+        *                                      lock->writelocked=true
+        *                                      unlock(m->wait_lock)
+        *
+        *                                      write_unlock()
+        *                                      lock->writelocked=false
+        *                                      rtmutex_unlock(m)
+        *                      read_lock()
+        *                                      write_lock()
+        *                                      rtmutex_lock(m)
+        *                                      swait()
+        * rtmutex_lock(m)
+        *
+        * That would put Reader1 behind the writer waiting on
+        * Reader2 to call read_unlock() which might be unbound.
+        */
+       rt_mutex_init_waiter(&waiter, false);
+       rt_spin_lock_slowlock_locked(m, &waiter, flags);
+       /*
+        * The slowlock() above is guaranteed to return with the rtmutex is
+        * now held, so there can't be a writer active. Increment the reader
+        * count and immediately drop the rtmutex again.
+        */
+       atomic_inc(&lock->readers);
+       raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+       rt_spin_lock_slowunlock(m);
+
+       debug_rt_mutex_free_waiter(&waiter);
+}
+
+void __read_rt_unlock(struct rt_rw_lock *lock)
+{
+       struct rt_mutex *m = &lock->rtmutex;
+       struct task_struct *tsk;
+
+       /*
+        * sem->readers can only hit 0 when a writer is waiting for the
+        * active readers to leave the critical region.
+        */
+       if (!atomic_dec_and_test(&lock->readers))
+               return;
+
+       raw_spin_lock_irq(&m->wait_lock);
+       /*
+        * Wake the writer, i.e. the rtmutex owner. It might release the
+        * rtmutex concurrently in the fast path, but to clean up the rw
+        * lock it needs to acquire m->wait_lock. The worst case which can
+        * happen is a spurious wakeup.
+        */
+       tsk = rt_mutex_owner(m);
+       if (tsk)
+               wake_up_process(tsk);
+
+       raw_spin_unlock_irq(&m->wait_lock);
+}
+
+static void __write_unlock_common(struct rt_rw_lock *lock, int bias,
+                                 unsigned long flags)
+{
+       struct rt_mutex *m = &lock->rtmutex;
+
+       atomic_add(READER_BIAS - bias, &lock->readers);
+       raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+       rt_spin_lock_slowunlock(m);
+}
+
+void __sched __write_rt_lock(struct rt_rw_lock *lock)
+{
+       struct rt_mutex *m = &lock->rtmutex;
+       struct task_struct *self = current;
+       unsigned long flags;
+
+       /* Take the rtmutex as a first step */
+       __rt_spin_lock(m);
+
+       /* Force readers into slow path */
+       atomic_sub(READER_BIAS, &lock->readers);
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+
+       raw_spin_lock(&self->pi_lock);
+       self->saved_state = self->state;
+       __set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+       raw_spin_unlock(&self->pi_lock);
+
+       for (;;) {
+               /* Have all readers left the critical region? */
+               if (!atomic_read(&lock->readers)) {
+                       atomic_set(&lock->readers, WRITER_BIAS);
+                       raw_spin_lock(&self->pi_lock);
+                       __set_current_state_no_track(self->saved_state);
+                       self->saved_state = TASK_RUNNING;
+                       raw_spin_unlock(&self->pi_lock);
+                       raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+                       return;
+               }
+
+               raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+
+               if (atomic_read(&lock->readers) != 0)
+                       schedule();
+
+               raw_spin_lock_irqsave(&m->wait_lock, flags);
+
+               raw_spin_lock(&self->pi_lock);
+               __set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+               raw_spin_unlock(&self->pi_lock);
+       }
+}
+
+int __write_rt_trylock(struct rt_rw_lock *lock)
+{
+       struct rt_mutex *m = &lock->rtmutex;
+       unsigned long flags;
+
+       if (!__rt_mutex_trylock(m))
+               return 0;
+
+       atomic_sub(READER_BIAS, &lock->readers);
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+       if (!atomic_read(&lock->readers)) {
+               atomic_set(&lock->readers, WRITER_BIAS);
+               raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+               return 1;
+       }
+       __write_unlock_common(lock, 0, flags);
+       return 0;
+}
+
+void __write_rt_unlock(struct rt_rw_lock *lock)
+{
+       struct rt_mutex *m = &lock->rtmutex;
+       unsigned long flags;
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+       __write_unlock_common(lock, WRITER_BIAS, flags);
+}
+
+/* Map the reader biased implementation */
+static inline int do_read_rt_trylock(rwlock_t *rwlock)
+{
+       return __read_rt_trylock(rwlock);
+}
+
+static inline int do_write_rt_trylock(rwlock_t *rwlock)
+{
+       return __write_rt_trylock(rwlock);
+}
+
+static inline void do_read_rt_lock(rwlock_t *rwlock)
+{
+       __read_rt_lock(rwlock);
+}
+
+static inline void do_write_rt_lock(rwlock_t *rwlock)
+{
+       __write_rt_lock(rwlock);
+}
+
+static inline void do_read_rt_unlock(rwlock_t *rwlock)
+{
+       __read_rt_unlock(rwlock);
+}
+
+static inline void do_write_rt_unlock(rwlock_t *rwlock)
+{
+       __write_rt_unlock(rwlock);
+}
+
+static inline void do_rwlock_rt_init(rwlock_t *rwlock, const char *name,
+                                    struct lock_class_key *key)
+{
+       __rwlock_biased_rt_init(rwlock, name, key);
+}
+
+int __lockfunc rt_read_can_lock(rwlock_t *rwlock)
+{
+       return  atomic_read(&rwlock->readers) < 0;
+}
+
+int __lockfunc rt_write_can_lock(rwlock_t *rwlock)
+{
+       return atomic_read(&rwlock->readers) == READER_BIAS;
+}
+
+/*
+ * The common functions which get wrapped into the rwlock API.
+ */
+int __lockfunc rt_read_trylock(rwlock_t *rwlock)
+{
+       int ret;
+
+       sleeping_lock_inc();
+       migrate_disable();
+       ret = do_read_rt_trylock(rwlock);
+       if (ret) {
+               rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_);
+       } else {
+               migrate_enable();
+               sleeping_lock_dec();
+       }
+       return ret;
+}
+EXPORT_SYMBOL(rt_read_trylock);
+
+int __lockfunc rt_write_trylock(rwlock_t *rwlock)
+{
+       int ret;
+
+       sleeping_lock_inc();
+       migrate_disable();
+       ret = do_write_rt_trylock(rwlock);
+       if (ret) {
+               rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+       } else {
+               migrate_enable();
+               sleeping_lock_dec();
+       }
+       return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock);
+
+void __lockfunc rt_read_lock(rwlock_t *rwlock)
+{
+       sleeping_lock_inc();
+       migrate_disable();
+       rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
+       do_read_rt_lock(rwlock);
+}
+EXPORT_SYMBOL(rt_read_lock);
+
+void __lockfunc rt_write_lock(rwlock_t *rwlock)
+{
+       sleeping_lock_inc();
+       migrate_disable();
+       rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+       do_write_rt_lock(rwlock);
+}
+EXPORT_SYMBOL(rt_write_lock);
+
+void __lockfunc rt_read_unlock(rwlock_t *rwlock)
+{
+       rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+       do_read_rt_unlock(rwlock);
+       migrate_enable();
+       sleeping_lock_dec();
+}
+EXPORT_SYMBOL(rt_read_unlock);
+
+void __lockfunc rt_write_unlock(rwlock_t *rwlock)
+{
+       rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+       do_write_rt_unlock(rwlock);
+       migrate_enable();
+       sleeping_lock_dec();
+}
+EXPORT_SYMBOL(rt_write_unlock);
+
+void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key)
+{
+       do_rwlock_rt_init(rwlock, name, key);
+}
+EXPORT_SYMBOL(__rt_rwlock_init);
diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c
new file mode 100644
index 000000000000..26991ddb6c5a
--- /dev/null
+++ b/kernel/locking/rwsem-rt.c
@@ -0,0 +1,269 @@
+/*
+ */
+#include <linux/rwsem.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/export.h>
+
+#include "rtmutex_common.h"
+
+/*
+ * RT-specific reader/writer semaphores
+ *
+ * down_write()
+ *  1) Lock sem->rtmutex
+ *  2) Remove the reader BIAS to force readers into the slow path
+ *  3) Wait until all readers have left the critical region
+ *  4) Mark it write locked
+ *
+ * up_write()
+ *  1) Remove the write locked marker
+ *  2) Set the reader BIAS so readers can use the fast path again
+ *  3) Unlock sem->rtmutex to release blocked readers
+ *
+ * down_read()
+ *  1) Try fast path acquisition (reader BIAS is set)
+ *  2) Take sem->rtmutex.wait_lock which protects the writelocked flag
+ *  3) If !writelocked, acquire it for read
+ *  4) If writelocked, block on sem->rtmutex
+ *  5) unlock sem->rtmutex, goto 1)
+ *
+ * up_read()
+ *  1) Try fast path release (reader count != 1)
+ *  2) Wake the writer waiting in down_write()#3
+ *
+ * down_read()#3 has the consequence, that rw semaphores on RT are not writer
+ * fair, but writers, which should be avoided in RT tasks (think mmap_sem),
+ * are subject to the rtmutex priority/DL inheritance mechanism.
+ *
+ * It's possible to make the rw semaphores writer fair by keeping a list of
+ * active readers. A blocked writer would force all newly incoming readers to
+ * block on the rtmutex, but the rtmutex would have to be proxy locked for one
+ * reader after the other. We can't use multi-reader inheritance because there
+ * is no way to support that with SCHED_DEADLINE. Implementing the one by one
+ * reader boosting/handover mechanism is a major surgery for a very dubious
+ * value.
+ *
+ * The risk of writer starvation is there, but the pathological use cases
+ * which trigger it are not necessarily the typical RT workloads.
+ */
+
+void __rwsem_init(struct rw_semaphore *sem, const char *name,
+                 struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+       /*
+        * Make sure we are not reinitializing a held semaphore:
+        */
+       debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+       lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+       atomic_set(&sem->readers, READER_BIAS);
+}
+EXPORT_SYMBOL(__rwsem_init);
+
+int __down_read_trylock(struct rw_semaphore *sem)
+{
+       int r, old;
+
+       /*
+        * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is
+        * set.
+        */
+       for (r = atomic_read(&sem->readers); r < 0;) {
+               old = atomic_cmpxchg(&sem->readers, r, r + 1);
+               if (likely(old == r))
+                       return 1;
+               r = old;
+       }
+       return 0;
+}
+
+void __sched __down_read(struct rw_semaphore *sem)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+       struct rt_mutex_waiter waiter;
+
+       if (__down_read_trylock(sem))
+               return;
+
+       might_sleep();
+       raw_spin_lock_irq(&m->wait_lock);
+       /*
+        * Allow readers as long as the writer has not completely
+        * acquired the semaphore for write.
+        */
+       if (atomic_read(&sem->readers) != WRITER_BIAS) {
+               atomic_inc(&sem->readers);
+               raw_spin_unlock_irq(&m->wait_lock);
+               return;
+       }
+
+       /*
+        * Call into the slow lock path with the rtmutex->wait_lock
+        * held, so this can't result in the following race:
+        *
+        * Reader1              Reader2         Writer
+        *                      down_read()
+        *                                      down_write()
+        *                                      rtmutex_lock(m)
+        *                                      swait()
+        * down_read()
+        * unlock(m->wait_lock)
+        *                      up_read()
+        *                      swake()
+        *                                      lock(m->wait_lock)
+        *                                      sem->writelocked=true
+        *                                      unlock(m->wait_lock)
+        *
+        *                                      up_write()
+        *                                      sem->writelocked=false
+        *                                      rtmutex_unlock(m)
+        *                      down_read()
+        *                                      down_write()
+        *                                      rtmutex_lock(m)
+        *                                      swait()
+        * rtmutex_lock(m)
+        *
+        * That would put Reader1 behind the writer waiting on
+        * Reader2 to call up_read() which might be unbound.
+        */
+       rt_mutex_init_waiter(&waiter, false);
+       rt_mutex_slowlock_locked(m, TASK_UNINTERRUPTIBLE, NULL,
+                                RT_MUTEX_MIN_CHAINWALK, NULL,
+                                &waiter);
+       /*
+        * The slowlock() above is guaranteed to return with the rtmutex is
+        * now held, so there can't be a writer active. Increment the reader
+        * count and immediately drop the rtmutex again.
+        */
+       atomic_inc(&sem->readers);
+       raw_spin_unlock_irq(&m->wait_lock);
+       __rt_mutex_unlock(m);
+
+       debug_rt_mutex_free_waiter(&waiter);
+}
+
+void __up_read(struct rw_semaphore *sem)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+       struct task_struct *tsk;
+
+       /*
+        * sem->readers can only hit 0 when a writer is waiting for the
+        * active readers to leave the critical region.
+        */
+       if (!atomic_dec_and_test(&sem->readers))
+               return;
+
+       might_sleep();
+       raw_spin_lock_irq(&m->wait_lock);
+       /*
+        * Wake the writer, i.e. the rtmutex owner. It might release the
+        * rtmutex concurrently in the fast path (due to a signal), but to
+        * clean up the rwsem it needs to acquire m->wait_lock. The worst
+        * case which can happen is a spurious wakeup.
+        */
+       tsk = rt_mutex_owner(m);
+       if (tsk)
+               wake_up_process(tsk);
+
+       raw_spin_unlock_irq(&m->wait_lock);
+}
+
+static void __up_write_unlock(struct rw_semaphore *sem, int bias,
+                             unsigned long flags)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+
+       atomic_add(READER_BIAS - bias, &sem->readers);
+       raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+       __rt_mutex_unlock(m);
+}
+
+static int __sched __down_write_common(struct rw_semaphore *sem, int state)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+       unsigned long flags;
+
+       /* Take the rtmutex as a first step */
+       if (__rt_mutex_lock_state(m, state))
+               return -EINTR;
+
+       /* Force readers into slow path */
+       atomic_sub(READER_BIAS, &sem->readers);
+       might_sleep();
+
+       set_current_state(state);
+       for (;;) {
+               raw_spin_lock_irqsave(&m->wait_lock, flags);
+               /* Have all readers left the critical region? */
+               if (!atomic_read(&sem->readers)) {
+                       atomic_set(&sem->readers, WRITER_BIAS);
+                       __set_current_state(TASK_RUNNING);
+                       raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+                       return 0;
+               }
+
+               if (signal_pending_state(state, current)) {
+                       __set_current_state(TASK_RUNNING);
+                       __up_write_unlock(sem, 0, flags);
+                       return -EINTR;
+               }
+               raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+
+               if (atomic_read(&sem->readers) != 0) {
+                       schedule();
+                       set_current_state(state);
+               }
+       }
+}
+
+void __sched __down_write(struct rw_semaphore *sem)
+{
+       __down_write_common(sem, TASK_UNINTERRUPTIBLE);
+}
+
+int __sched __down_write_killable(struct rw_semaphore *sem)
+{
+       return __down_write_common(sem, TASK_KILLABLE);
+}
+
+int __down_write_trylock(struct rw_semaphore *sem)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+       unsigned long flags;
+
+       if (!__rt_mutex_trylock(m))
+               return 0;
+
+       atomic_sub(READER_BIAS, &sem->readers);
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+       if (!atomic_read(&sem->readers)) {
+               atomic_set(&sem->readers, WRITER_BIAS);
+               raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+               return 1;
+       }
+       __up_write_unlock(sem, 0, flags);
+       return 0;
+}
+
+void __up_write(struct rw_semaphore *sem)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+       unsigned long flags;
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+       __up_write_unlock(sem, WRITER_BIAS, flags);
+}
+
+void __downgrade_write(struct rw_semaphore *sem)
+{
+       struct rt_mutex *m = &sem->rtmutex;
+       unsigned long flags;
+
+       raw_spin_lock_irqsave(&m->wait_lock, flags);
+       /* Release it and account current as reader */
+       __up_write_unlock(sem, WRITER_BIAS - 1, flags);
+}
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 6e40fdfba326..401bda23f786 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -125,8 +125,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock)           \
  *         __[spin|read|write]_lock_bh()
  */
 BUILD_LOCK_OPS(spin, raw_spinlock);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
 BUILD_LOCK_OPS(read, rwlock);
 BUILD_LOCK_OPS(write, rwlock);
+#endif
 
 #endif
 
@@ -210,6 +213,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
 EXPORT_SYMBOL(_raw_spin_unlock_bh);
 #endif
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #ifndef CONFIG_INLINE_READ_TRYLOCK
 int __lockfunc _raw_read_trylock(rwlock_t *lock)
 {
@@ -354,6 +359,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
 EXPORT_SYMBOL(_raw_write_unlock_bh);
 #endif
 
+#endif /* !PREEMPT_RT_FULL */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 9aa0fccd5d43..76d0b40d9193 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
 
 EXPORT_SYMBOL(__raw_spin_lock_init);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void __rwlock_init(rwlock_t *lock, const char *name,
                   struct lock_class_key *key)
 {
@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name,
 }
 
 EXPORT_SYMBOL(__rwlock_init);
+#endif
 
 static void spin_dump(raw_spinlock_t *lock, const char *msg)
 {
@@ -135,6 +137,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock)
        arch_spin_unlock(&lock->raw_lock);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 static void rwlock_bug(rwlock_t *lock, const char *msg)
 {
        if (!debug_locks_off())
@@ -224,3 +227,5 @@ void do_raw_write_unlock(rwlock_t *lock)
        debug_write_unlock(lock);
        arch_write_unlock(&lock->raw_lock);
 }
+
+#endif
diff --git a/kernel/panic.c b/kernel/panic.c
index bdd18afa19a4..5da649633795 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -482,9 +482,11 @@ static u64 oops_id;
 
 static int init_oops_id(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
        if (!oops_id)
                get_random_bytes(&oops_id, sizeof(oops_id));
        else
+#endif
                oops_id++;
 
        return 0;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index a5c36e9c56a6..a4b83cb0c6e5 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -287,6 +287,8 @@ static int create_image(int platform_mode)
 
        local_irq_disable();
 
+       system_state = SYSTEM_SUSPEND;
+
        error = syscore_suspend();
        if (error) {
                pr_err("Some system devices failed to power down, aborting hibernation\n");
@@ -317,6 +319,7 @@ static int create_image(int platform_mode)
        syscore_resume();
 
  Enable_irqs:
+       system_state = SYSTEM_RUNNING;
        local_irq_enable();
 
  Enable_cpus:
@@ -445,6 +448,7 @@ static int resume_target_kernel(bool platform_mode)
                goto Enable_cpus;
 
        local_irq_disable();
+       system_state = SYSTEM_SUSPEND;
 
        error = syscore_suspend();
        if (error)
@@ -478,6 +482,7 @@ static int resume_target_kernel(bool platform_mode)
        syscore_resume();
 
  Enable_irqs:
+       system_state = SYSTEM_RUNNING;
        local_irq_enable();
 
  Enable_cpus:
@@ -563,6 +568,7 @@ int hibernation_platform_enter(void)
                goto Enable_cpus;
 
        local_irq_disable();
+       system_state = SYSTEM_SUSPEND;
        syscore_suspend();
        if (pm_wakeup_pending()) {
                error = -EAGAIN;
@@ -575,6 +581,7 @@ int hibernation_platform_enter(void)
 
  Power_up:
        syscore_resume();
+       system_state = SYSTEM_RUNNING;
        local_irq_enable();
 
  Enable_cpus:
@@ -672,6 +679,10 @@ static int load_image_and_restore(void)
        return error;
 }
 
+#ifndef CONFIG_SUSPEND
+bool pm_in_action;
+#endif
+
 /**
  * hibernate - Carry out system hibernation, including saving the image.
  */
@@ -685,6 +696,8 @@ int hibernate(void)
                return -EPERM;
        }
 
+       pm_in_action = true;
+
        lock_system_sleep();
        /* The snapshot device should not be opened while we're running */
        if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
@@ -763,6 +776,7 @@ int hibernate(void)
        atomic_inc(&snapshot_device_available);
  Unlock:
        unlock_system_sleep();
+       pm_in_action = false;
        pr_info("hibernation exit\n");
 
        return error;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c0bc2c89697a..b89605fe0e88 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -27,6 +27,7 @@
 #include <linux/export.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
+#include <linux/swait.h>
 #include <linux/ftrace.h>
 #include <trace/events/power.h>
 #include <linux/compiler.h>
@@ -57,7 +58,7 @@ EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
 
 static const struct platform_suspend_ops *suspend_ops;
 static const struct platform_s2idle_ops *s2idle_ops;
-static DECLARE_WAIT_QUEUE_HEAD(s2idle_wait_head);
+static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head);
 
 enum s2idle_states __read_mostly s2idle_state;
 static DEFINE_RAW_SPINLOCK(s2idle_lock);
@@ -91,8 +92,8 @@ static void s2idle_enter(void)
        /* Push all the CPUs into the idle loop. */
        wake_up_all_idle_cpus();
        /* Make the current CPU wait so it can enter the idle loop too. */
-       wait_event(s2idle_wait_head,
-                  s2idle_state == S2IDLE_STATE_WAKE);
+       swait_event(s2idle_wait_head,
+                   s2idle_state == S2IDLE_STATE_WAKE);
 
        cpuidle_pause();
        put_online_cpus();
@@ -159,7 +160,7 @@ void s2idle_wake(void)
        raw_spin_lock_irqsave(&s2idle_lock, flags);
        if (s2idle_state > S2IDLE_STATE_NONE) {
                s2idle_state = S2IDLE_STATE_WAKE;
-               wake_up(&s2idle_wait_head);
+               swake_up(&s2idle_wait_head);
        }
        raw_spin_unlock_irqrestore(&s2idle_lock, flags);
 }
@@ -428,6 +429,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
        arch_suspend_disable_irqs();
        BUG_ON(!irqs_disabled());
 
+       system_state = SYSTEM_SUSPEND;
+
        error = syscore_suspend();
        if (!error) {
                *wakeup = pm_wakeup_pending();
@@ -443,6 +446,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
                syscore_resume();
        }
 
+       system_state = SYSTEM_RUNNING;
+
        arch_suspend_enable_irqs();
        BUG_ON(irqs_disabled());
 
@@ -589,6 +594,8 @@ static int enter_state(suspend_state_t state)
        return error;
 }
 
+bool pm_in_action;
+
 /**
  * pm_suspend - Externally visible function for suspending the system.
  * @state: System sleep state to enter.
@@ -603,6 +610,7 @@ int pm_suspend(suspend_state_t state)
        if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
                return -EINVAL;
 
+       pm_in_action = true;
        pr_info("suspend entry (%s)\n", mem_sleep_labels[state]);
        error = enter_state(state);
        if (error) {
@@ -612,6 +620,7 @@ int pm_suspend(suspend_state_t state)
                suspend_stats.success++;
        }
        pr_info("suspend exit\n");
+       pm_in_action = false;
        return error;
 }
 EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index f0223a7d9ed1..13fd0bcf2367 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1348,6 +1348,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 {
        char *text;
        int len = 0;
+       int attempts = 0;
+       int num_msg;
 
        text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
        if (!text)
@@ -1359,6 +1361,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                u64 seq;
                u32 idx;
 
+try_again:
+               attempts++;
+               if (attempts > 10) {
+                       len = -EBUSY;
+                       goto out;
+               }
+               num_msg = 0;
+
                /*
                 * Find first record that fits, including all following records,
                 * into the user-provided buffer for this dump.
@@ -1371,6 +1381,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                        len += msg_print_text(msg, true, NULL, 0);
                        idx = log_next(idx);
                        seq++;
+                       num_msg++;
+                       if (num_msg > 5) {
+                               num_msg = 0;
+                               logbuf_unlock_irq();
+                               logbuf_lock_irq();
+                               if (clear_seq < log_first_seq)
+                                       goto try_again;
+                       }
                }
 
                /* move first record forward until length fits into the buffer */
@@ -1382,6 +1400,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                        len -= msg_print_text(msg, true, NULL, 0);
                        idx = log_next(idx);
                        seq++;
+                       num_msg++;
+                       if (num_msg > 5) {
+                               num_msg = 0;
+                               logbuf_unlock_irq();
+                               logbuf_lock_irq();
+                               if (clear_seq < log_first_seq)
+                                       goto try_again;
+                       }
                }
 
                /* last message fitting into this dump */
@@ -1420,6 +1446,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                clear_seq = log_next_seq;
                clear_idx = log_next_idx;
        }
+out:
        logbuf_unlock_irq();
 
        kfree(text);
@@ -1558,6 +1585,12 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
        if (!console_drivers)
                return;
 
+       if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) {
+               if (in_irq() || in_nmi())
+                       return;
+       }
+
+       migrate_disable();
        for_each_console(con) {
                if (exclusive_console && con != exclusive_console)
                        continue;
@@ -1573,6 +1606,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
                else
                        con->write(con, text, len);
        }
+       migrate_enable();
 }
 
 int printk_delay_msec __read_mostly;
@@ -1757,12 +1791,22 @@ asmlinkage int vprintk_emit(int facility, int level,
 
        /* If called from the scheduler, we can not call up(). */
        if (!in_sched) {
+               int may_trylock = 1;
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+               /*
+                * we can't take a sleeping lock with IRQs or preeption disabled
+                * so we can't print in these contexts
+                */
+               if (!(preempt_count() == 0 && !irqs_disabled()))
+                       may_trylock = 0;
+#endif
                /*
                 * Try to acquire and then immediately release the console
                 * semaphore.  The release will print out buffers and wake up
                 * /dev/kmsg and syslog() users.
                 */
-               if (console_trylock())
+               if (may_trylock && console_trylock())
                        console_unlock();
        }
 
@@ -1872,26 +1916,6 @@ static bool suppress_message_printing(int level) { return false; }
 
 #endif /* CONFIG_PRINTK */
 
-#ifdef CONFIG_EARLY_PRINTK
-struct console *early_console;
-
-asmlinkage __visible void early_printk(const char *fmt, ...)
-{
-       va_list ap;
-       char buf[512];
-       int n;
-
-       if (!early_console)
-               return;
-
-       va_start(ap, fmt);
-       n = vscnprintf(buf, sizeof(buf), fmt, ap);
-       va_end(ap);
-
-       early_console->write(early_console, buf, n);
-}
-#endif
-
 static int __add_preferred_console(char *name, int idx, char *options,
                                   char *brl_options)
 {
@@ -2238,10 +2262,15 @@ void console_unlock(void)
                console_seq++;
                raw_spin_unlock(&logbuf_lock);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+               printk_safe_exit_irqrestore(flags);
+               call_console_drivers(ext_text, ext_len, text, len);
+#else
                stop_critical_timings();        /* don't trace print latency */
                call_console_drivers(ext_text, ext_len, text, len);
                start_critical_timings();
                printk_safe_exit_irqrestore(flags);
+#endif
 
                if (do_cond_resched)
                        cond_resched();
@@ -2295,6 +2324,11 @@ void console_unblank(void)
 {
        struct console *c;
 
+       if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) {
+               if (in_irq() || in_nmi())
+                       return;
+       }
+
        /*
         * console_unblank can no longer be called in interrupt context unless
         * oops_in_progress is set to 1..
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 64f8046586b6..a24e16bef51c 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -22,6 +22,7 @@
 #include <linux/cpumask.h>
 #include <linux/irq_work.h>
 #include <linux/printk.h>
+#include <linux/console.h>
 
 #include "internal.h"
 
@@ -373,8 +374,74 @@ void __printk_safe_exit(void)
        this_cpu_dec(printk_context);
 }
 
+#ifdef CONFIG_EARLY_PRINTK
+struct console *early_console;
+
+static void early_vprintk(const char *fmt, va_list ap)
+{
+       if (early_console) {
+               char buf[512];
+               int n = vscnprintf(buf, sizeof(buf), fmt, ap);
+
+               early_console->write(early_console, buf, n);
+       }
+}
+
+asmlinkage void early_printk(const char *fmt, ...)
+{
+       va_list ap;
+
+       va_start(ap, fmt);
+       early_vprintk(fmt, ap);
+       va_end(ap);
+}
+
+/*
+ * This is independent of any log levels - a global
+ * kill switch that turns off all of printk.
+ *
+ * Used by the NMI watchdog if early-printk is enabled.
+ */
+static bool __read_mostly printk_killswitch;
+
+static int __init force_early_printk_setup(char *str)
+{
+       printk_killswitch = true;
+       return 0;
+}
+early_param("force_early_printk", force_early_printk_setup);
+
+void printk_kill(void)
+{
+       printk_killswitch = true;
+}
+
+#ifdef CONFIG_PRINTK
+static int forced_early_printk(const char *fmt, va_list ap)
+{
+       if (!printk_killswitch)
+               return 0;
+       early_vprintk(fmt, ap);
+       return 1;
+}
+#endif
+
+#else
+static inline int forced_early_printk(const char *fmt, va_list ap)
+{
+       return 0;
+}
+#endif
+
 __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 {
+       /*
+        * Fall back to early_printk if a debugging subsystem has
+        * killed printk output
+        */
+       if (unlikely(forced_early_printk(fmt, args)))
+               return 1;
+
        /*
         * Try to use the main logbuf even in NMI. But avoid calling console
         * drivers that might have their own locks.
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 84b1367935e4..b32a86f63522 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -175,7 +175,14 @@ static bool ptrace_freeze_traced(struct task_struct *task)
 
        spin_lock_irq(&task->sighand->siglock);
        if (task_is_traced(task) && !__fatal_signal_pending(task)) {
-               task->state = __TASK_TRACED;
+               unsigned long flags;
+
+               raw_spin_lock_irqsave(&task->pi_lock, flags);
+               if (task->state & __TASK_TRACED)
+                       task->state = __TASK_TRACED;
+               else
+                       task->saved_state = __TASK_TRACED;
+               raw_spin_unlock_irqrestore(&task->pi_lock, flags);
                ret = true;
        }
        spin_unlock_irq(&task->sighand->siglock);
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 9210379c0353..0be2c96fb640 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -36,7 +36,7 @@ config TINY_RCU
 
 config RCU_EXPERT
        bool "Make expert-level adjustments to RCU configuration"
-       default n
+       default y if PREEMPT_RT_FULL
        help
          This option needs to be enabled if you wish to make
          expert-level adjustments to RCU configuration.  By default,
@@ -172,7 +172,7 @@ config RCU_FANOUT_LEAF
 
 config RCU_FAST_NO_HZ
        bool "Accelerate last non-dyntick-idle CPU's grace periods"
-       depends on NO_HZ_COMMON && SMP && RCU_EXPERT
+       depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL
        default n
        help
          This option permits CPUs to enter dynticks-idle state even if
@@ -191,7 +191,7 @@ config RCU_FAST_NO_HZ
 config RCU_BOOST
        bool "Enable RCU priority boosting"
        depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
-       default n
+       default y if PREEMPT_RT_FULL
        help
          This option boosts the priority of preempted RCU readers that
          block the current preemptible RCU grace period for too long.
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index e4b43fef89f5..0b056c30e9b1 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -462,18 +462,26 @@ static inline void show_rcu_gp_kthreads(void) { }
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
 unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
 unsigned long rcu_batches_started_sched(void);
 unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
 unsigned long rcu_batches_completed_sched(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
 void rcu_force_quiescent_state(void);
-void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+void rcu_bh_force_quiescent_state(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_completed_bh(void);
+#else
+# define rcu_bh_force_quiescent_state  rcu_force_quiescent_state
+# define rcu_batches_completed_bh      rcu_batches_completed
+# define rcu_batches_started_bh                rcu_batches_completed
+#endif
+
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
 #ifdef CONFIG_RCU_NOCB_CPU
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 7649fcd2c4c7..88cba7c2956c 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/rcupdate.h>
 
 #include "rcu_segcblist.h"
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 45f2ffbc1e78..2e9dbb734d5a 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -417,6 +417,7 @@ static struct rcu_torture_ops rcu_ops = {
        .name           = "rcu"
 };
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Definitions for rcu_bh torture testing.
  */
@@ -456,6 +457,12 @@ static struct rcu_torture_ops rcu_bh_ops = {
        .name           = "rcu_bh"
 };
 
+#else
+static struct rcu_torture_ops rcu_bh_ops = {
+       .ttype          = INVALID_RCU_FLAVOR,
+};
+#endif
+
 /*
  * Don't even think about trying any of these in real life!!!
  * The names includes "busted", and they really means it!
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 6d5880089ff6..0e3b2bd3f2ac 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -36,6 +36,8 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/srcu.h>
+#include <linux/cpu.h>
+#include <linux/locallock.h>
 
 #include "rcu.h"
 #include "rcu_segcblist.h"
@@ -53,6 +55,33 @@ static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
 
+/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
+#define spin_lock_rcu_node(p)                                  \
+do {                                                                   \
+       spin_lock(&ACCESS_PRIVATE(p, lock));                    \
+       smp_mb__after_unlock_lock();                                    \
+} while (0)
+
+#define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock))
+
+#define spin_lock_irq_rcu_node(p)                                      \
+do {                                                                   \
+       spin_lock_irq(&ACCESS_PRIVATE(p, lock));                        \
+       smp_mb__after_unlock_lock();                                    \
+} while (0)
+
+#define spin_unlock_irq_rcu_node(p)                                    \
+       spin_unlock_irq(&ACCESS_PRIVATE(p, lock))
+
+#define spin_lock_irqsave_rcu_node(p, flags)                   \
+do {                                                                   \
+       spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);     \
+       smp_mb__after_unlock_lock();                                    \
+} while (0)
+
+#define spin_unlock_irqrestore_rcu_node(p, flags)                      \
+       spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \
+
 /*
  * Initialize SRCU combining tree.  Note that statically allocated
  * srcu_struct structures might already have srcu_read_lock() and
@@ -77,7 +106,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
 
        /* Each pass through this loop initializes one srcu_node structure. */
        rcu_for_each_node_breadth_first(sp, snp) {
-               raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock));
+               spin_lock_init(&ACCESS_PRIVATE(snp, lock));
                WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
                             ARRAY_SIZE(snp->srcu_data_have_cbs));
                for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
@@ -111,7 +140,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
        snp_first = sp->level[level];
        for_each_possible_cpu(cpu) {
                sdp = per_cpu_ptr(sp->sda, cpu);
-               raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
+               spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
                rcu_segcblist_init(&sdp->srcu_cblist);
                sdp->srcu_cblist_invoking = false;
                sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
@@ -170,7 +199,7 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name,
        /* Don't re-initialize a lock while it is held. */
        debug_check_no_locks_freed((void *)sp, sizeof(*sp));
        lockdep_init_map(&sp->dep_map, name, key, 0);
-       raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock));
+       spin_lock_init(&ACCESS_PRIVATE(sp, lock));
        return init_srcu_struct_fields(sp, false);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
@@ -187,7 +216,7 @@ EXPORT_SYMBOL_GPL(__init_srcu_struct);
  */
 int init_srcu_struct(struct srcu_struct *sp)
 {
-       raw_spin_lock_init(&ACCESS_PRIVATE(sp, lock));
+       spin_lock_init(&ACCESS_PRIVATE(sp, lock));
        return init_srcu_struct_fields(sp, false);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
@@ -210,13 +239,13 @@ static void check_init_srcu_struct(struct srcu_struct *sp)
        /* The smp_load_acquire() pairs with the smp_store_release(). */
        if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
                return; /* Already initialized. */
-       raw_spin_lock_irqsave_rcu_node(sp, flags);
+       spin_lock_irqsave_rcu_node(sp, flags);
        if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
-               raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+               spin_unlock_irqrestore_rcu_node(sp, flags);
                return;
        }
        init_srcu_struct_fields(sp, true);
-       raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+       spin_unlock_irqrestore_rcu_node(sp, flags);
 }
 
 /*
@@ -424,21 +453,6 @@ static void srcu_gp_start(struct srcu_struct *sp)
        WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
 
-/*
- * Track online CPUs to guide callback workqueue placement.
- */
-DEFINE_PER_CPU(bool, srcu_online);
-
-void srcu_online_cpu(unsigned int cpu)
-{
-       WRITE_ONCE(per_cpu(srcu_online, cpu), true);
-}
-
-void srcu_offline_cpu(unsigned int cpu)
-{
-       WRITE_ONCE(per_cpu(srcu_online, cpu), false);
-}
-
 /*
  * Place the workqueue handler on the specified CPU if online, otherwise
  * just run it whereever.  This is useful for placing workqueue handlers
@@ -450,12 +464,12 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 {
        bool ret;
 
-       preempt_disable();
-       if (READ_ONCE(per_cpu(srcu_online, cpu)))
+       cpus_read_lock();
+       if (cpu_online(cpu))
                ret = queue_delayed_work_on(cpu, wq, dwork, delay);
        else
                ret = queue_delayed_work(wq, dwork, delay);
-       preempt_enable();
+       cpus_read_unlock();
        return ret;
 }
 
@@ -513,7 +527,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
        mutex_lock(&sp->srcu_cb_mutex);
 
        /* End the current grace period. */
-       raw_spin_lock_irq_rcu_node(sp);
+       spin_lock_irq_rcu_node(sp);
        idx = rcu_seq_state(sp->srcu_gp_seq);
        WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
        cbdelay = srcu_get_delay(sp);
@@ -522,7 +536,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
        gpseq = rcu_seq_current(&sp->srcu_gp_seq);
        if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
                sp->srcu_gp_seq_needed_exp = gpseq;
-       raw_spin_unlock_irq_rcu_node(sp);
+       spin_unlock_irq_rcu_node(sp);
        mutex_unlock(&sp->srcu_gp_mutex);
        /* A new grace period can start at this point.  But only one. */
 
@@ -530,7 +544,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
        idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
        idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
        rcu_for_each_node_breadth_first(sp, snp) {
-               raw_spin_lock_irq_rcu_node(snp);
+               spin_lock_irq_rcu_node(snp);
                cbs = false;
                if (snp >= sp->level[rcu_num_lvls - 1])
                        cbs = snp->srcu_have_cbs[idx] == gpseq;
@@ -540,7 +554,7 @@ static void srcu_gp_end(struct srcu_struct *sp)
                        snp->srcu_gp_seq_needed_exp = gpseq;
                mask = snp->srcu_data_have_cbs[idx];
                snp->srcu_data_have_cbs[idx] = 0;
-               raw_spin_unlock_irq_rcu_node(snp);
+               spin_unlock_irq_rcu_node(snp);
                if (cbs)
                        srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
 
@@ -548,11 +562,11 @@ static void srcu_gp_end(struct srcu_struct *sp)
                if (!(gpseq & counter_wrap_check))
                        for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
                                sdp = per_cpu_ptr(sp->sda, cpu);
-                               raw_spin_lock_irqsave_rcu_node(sdp, flags);
+                               spin_lock_irqsave_rcu_node(sdp, flags);
                                if (ULONG_CMP_GE(gpseq,
                                                 sdp->srcu_gp_seq_needed + 100))
                                        sdp->srcu_gp_seq_needed = gpseq;
-                               raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
+                               spin_unlock_irqrestore_rcu_node(sdp, flags);
                        }
        }
 
@@ -560,17 +574,17 @@ static void srcu_gp_end(struct srcu_struct *sp)
        mutex_unlock(&sp->srcu_cb_mutex);
 
        /* Start a new grace period if needed. */
-       raw_spin_lock_irq_rcu_node(sp);
+       spin_lock_irq_rcu_node(sp);
        gpseq = rcu_seq_current(&sp->srcu_gp_seq);
        if (!rcu_seq_state(gpseq) &&
            ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
                srcu_gp_start(sp);
-               raw_spin_unlock_irq_rcu_node(sp);
+               spin_unlock_irq_rcu_node(sp);
                /* Throttle expedited grace periods: Should be rare! */
                srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff
                                    ? 0 : SRCU_INTERVAL);
        } else {
-               raw_spin_unlock_irq_rcu_node(sp);
+               spin_unlock_irq_rcu_node(sp);
        }
 }
 
@@ -590,18 +604,18 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
                if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
                    ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
                        return;
-               raw_spin_lock_irqsave_rcu_node(snp, flags);
+               spin_lock_irqsave_rcu_node(snp, flags);
                if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
-                       raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+                       spin_unlock_irqrestore_rcu_node(snp, flags);
                        return;
                }
                WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
-               raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+               spin_unlock_irqrestore_rcu_node(snp, flags);
        }
-       raw_spin_lock_irqsave_rcu_node(sp, flags);
+       spin_lock_irqsave_rcu_node(sp, flags);
        if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
                sp->srcu_gp_seq_needed_exp = s;
-       raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+       spin_unlock_irqrestore_rcu_node(sp, flags);
 }
 
 /*
@@ -623,12 +637,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
        for (; snp != NULL; snp = snp->srcu_parent) {
                if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
                        return; /* GP already done and CBs recorded. */
-               raw_spin_lock_irqsave_rcu_node(snp, flags);
+               spin_lock_irqsave_rcu_node(snp, flags);
                if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
                        snp_seq = snp->srcu_have_cbs[idx];
                        if (snp == sdp->mynode && snp_seq == s)
                                snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
-                       raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+                       spin_unlock_irqrestore_rcu_node(snp, flags);
                        if (snp == sdp->mynode && snp_seq != s) {
                                srcu_schedule_cbs_sdp(sdp, do_norm
                                                           ? SRCU_INTERVAL
@@ -644,11 +658,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
                        snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
                if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
                        snp->srcu_gp_seq_needed_exp = s;
-               raw_spin_unlock_irqrestore_rcu_node(snp, flags);
+               spin_unlock_irqrestore_rcu_node(snp, flags);
        }
 
        /* Top of tree, must ensure the grace period will be started. */
-       raw_spin_lock_irqsave_rcu_node(sp, flags);
+       spin_lock_irqsave_rcu_node(sp, flags);
        if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
                /*
                 * Record need for grace period s.  Pair with load
@@ -667,7 +681,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
                queue_delayed_work(system_power_efficient_wq, &sp->work,
                                   srcu_get_delay(sp));
        }
-       raw_spin_unlock_irqrestore_rcu_node(sp, flags);
+       spin_unlock_irqrestore_rcu_node(sp, flags);
 }
 
 /*
@@ -736,6 +750,8 @@ static void srcu_flip(struct srcu_struct *sp)
  * negligible when amoritized over that time period, and the extra latency
  * of a needlessly non-expedited grace period is similarly negligible.
  */
+static DEFINE_LOCAL_IRQ_LOCK(sp_llock);
+
 static bool srcu_might_be_idle(struct srcu_struct *sp)
 {
        unsigned long curseq;
@@ -744,13 +760,13 @@ static bool srcu_might_be_idle(struct srcu_struct *sp)
        unsigned long t;
 
        /* If the local srcu_data structure has callbacks, not idle.  */
-       local_irq_save(flags);
+       local_lock_irqsave(sp_llock, flags);
        sdp = this_cpu_ptr(sp->sda);
        if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
-               local_irq_restore(flags);
+               local_unlock_irqrestore(sp_llock, flags);
                return false; /* Callbacks already present, so not idle. */
        }
-       local_irq_restore(flags);
+       local_unlock_irqrestore(sp_llock, flags);
 
        /*
         * No local callbacks, so probabalistically probe global state.
@@ -828,9 +844,9 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
                return;
        }
        rhp->func = func;
-       local_irq_save(flags);
+       local_lock_irqsave(sp_llock, flags);
        sdp = this_cpu_ptr(sp->sda);
-       raw_spin_lock_rcu_node(sdp);
+       spin_lock_rcu_node(sdp);
        rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
        rcu_segcblist_advance(&sdp->srcu_cblist,
                              rcu_seq_current(&sp->srcu_gp_seq));
@@ -844,7 +860,8 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
                sdp->srcu_gp_seq_needed_exp = s;
                needexp = true;
        }
-       raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
+       spin_unlock_rcu_node(sdp);
+       local_unlock_irqrestore(sp_llock, flags);
        if (needgp)
                srcu_funnel_gp_start(sp, sdp, s, do_norm);
        else if (needexp)
@@ -900,7 +917,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
 
        /*
         * Make sure that later code is ordered after the SRCU grace
-        * period.  This pairs with the raw_spin_lock_irq_rcu_node()
+        * period.  This pairs with the spin_lock_irq_rcu_node()
         * in srcu_invoke_callbacks().  Unlike Tree RCU, this is needed
         * because the current CPU might have been totally uninvolved with
         * (and thus unordered against) that grace period.
@@ -1024,7 +1041,7 @@ void srcu_barrier(struct srcu_struct *sp)
         */
        for_each_possible_cpu(cpu) {
                sdp = per_cpu_ptr(sp->sda, cpu);
-               raw_spin_lock_irq_rcu_node(sdp);
+               spin_lock_irq_rcu_node(sdp);
                atomic_inc(&sp->srcu_barrier_cpu_cnt);
                sdp->srcu_barrier_head.func = srcu_barrier_cb;
                debug_rcu_head_queue(&sdp->srcu_barrier_head);
@@ -1033,7 +1050,7 @@ void srcu_barrier(struct srcu_struct *sp)
                        debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
                        atomic_dec(&sp->srcu_barrier_cpu_cnt);
                }
-               raw_spin_unlock_irq_rcu_node(sdp);
+               spin_unlock_irq_rcu_node(sdp);
        }
 
        /* Remove the initial count, at which point reaching zero can happen. */
@@ -1082,17 +1099,17 @@ static void srcu_advance_state(struct srcu_struct *sp)
         */
        idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
        if (idx == SRCU_STATE_IDLE) {
-               raw_spin_lock_irq_rcu_node(sp);
+               spin_lock_irq_rcu_node(sp);
                if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
                        WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
-                       raw_spin_unlock_irq_rcu_node(sp);
+                       spin_unlock_irq_rcu_node(sp);
                        mutex_unlock(&sp->srcu_gp_mutex);
                        return;
                }
                idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
                if (idx == SRCU_STATE_IDLE)
                        srcu_gp_start(sp);
-               raw_spin_unlock_irq_rcu_node(sp);
+               spin_unlock_irq_rcu_node(sp);
                if (idx != SRCU_STATE_IDLE) {
                        mutex_unlock(&sp->srcu_gp_mutex);
                        return; /* Someone else started the grace period. */
@@ -1141,19 +1158,19 @@ static void srcu_invoke_callbacks(struct work_struct *work)
        sdp = container_of(work, struct srcu_data, work.work);
        sp = sdp->sp;
        rcu_cblist_init(&ready_cbs);
-       raw_spin_lock_irq_rcu_node(sdp);
+       spin_lock_irq_rcu_node(sdp);
        rcu_segcblist_advance(&sdp->srcu_cblist,
                              rcu_seq_current(&sp->srcu_gp_seq));
        if (sdp->srcu_cblist_invoking ||
            !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
-               raw_spin_unlock_irq_rcu_node(sdp);
+               spin_unlock_irq_rcu_node(sdp);
                return;  /* Someone else on the job or nothing to do. */
        }
 
        /* We are on the job!  Extract and invoke ready callbacks. */
        sdp->srcu_cblist_invoking = true;
        rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
-       raw_spin_unlock_irq_rcu_node(sdp);
+       spin_unlock_irq_rcu_node(sdp);
        rhp = rcu_cblist_dequeue(&ready_cbs);
        for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
                debug_rcu_head_unqueue(rhp);
@@ -1166,13 +1183,13 @@ static void srcu_invoke_callbacks(struct work_struct *work)
         * Update counts, accelerate new callbacks, and if needed,
         * schedule another round of callback invocation.
         */
-       raw_spin_lock_irq_rcu_node(sdp);
+       spin_lock_irq_rcu_node(sdp);
        rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
        (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
                                       rcu_seq_snap(&sp->srcu_gp_seq));
        sdp->srcu_cblist_invoking = false;
        more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
-       raw_spin_unlock_irq_rcu_node(sdp);
+       spin_unlock_irq_rcu_node(sdp);
        if (more)
                srcu_schedule_cbs_sdp(sdp, 0);
 }
@@ -1185,7 +1202,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
 {
        bool pushgp = true;
 
-       raw_spin_lock_irq_rcu_node(sp);
+       spin_lock_irq_rcu_node(sp);
        if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
                if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
                        /* All requests fulfilled, time to go idle. */
@@ -1195,7 +1212,7 @@ static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
                /* Outstanding request and no GP.  Start one. */
                srcu_gp_start(sp);
        }
-       raw_spin_unlock_irq_rcu_node(sp);
+       spin_unlock_irq_rcu_node(sp);
 
        if (pushgp)
                queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3e3650e94ae6..0a722b56d90b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -58,6 +58,11 @@
 #include <linux/trace_events.h>
 #include <linux/suspend.h>
 #include <linux/ftrace.h>
+#include <linux/delay.h>
+#include <linux/gfp.h>
+#include <linux/oom.h>
+#include <linux/smpboot.h>
+#include "../time/tick-internal.h"
 
 #include "tree.h"
 #include "rcu.h"
@@ -243,6 +248,19 @@ void rcu_sched_qs(void)
                           this_cpu_ptr(&rcu_sched_data), true);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void rcu_preempt_qs(void);
+
+void rcu_bh_qs(void)
+{
+       unsigned long flags;
+
+       /* Callers to this function, rcu_preempt_qs(), must disable irqs. */
+       local_irq_save(flags);
+       rcu_preempt_qs();
+       local_irq_restore(flags);
+}
+#else
 void rcu_bh_qs(void)
 {
        RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
@@ -253,6 +271,7 @@ void rcu_bh_qs(void)
                __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
        }
 }
+#endif
 
 /*
  * Steal a bit from the bottom of ->dynticks for idle entry/exit
@@ -564,11 +583,13 @@ EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
 /*
  * Return the number of RCU BH batches started thus far for debug & stats.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 unsigned long rcu_batches_started_bh(void)
 {
        return rcu_bh_state.gpnum;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+#endif
 
 /*
  * Return the number of RCU batches completed thus far for debug & stats.
@@ -588,6 +609,7 @@ unsigned long rcu_batches_completed_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Return the number of RCU BH batches completed thus far for debug & stats.
  */
@@ -596,6 +618,7 @@ unsigned long rcu_batches_completed_bh(void)
        return rcu_bh_state.completed;
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+#endif
 
 /*
  * Return the number of RCU expedited batches completed thus far for
@@ -619,6 +642,7 @@ unsigned long rcu_exp_batches_completed_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Force a quiescent state.
  */
@@ -637,6 +661,13 @@ void rcu_bh_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
 
+#else
+void rcu_force_quiescent_state(void)
+{
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+#endif
+
 /*
  * Force a quiescent state for RCU-sched.
  */
@@ -687,9 +718,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
        case RCU_FLAVOR:
                rsp = rcu_state_p;
                break;
+#ifndef CONFIG_PREEMPT_RT_FULL
        case RCU_BH_FLAVOR:
                rsp = &rcu_bh_state;
                break;
+#endif
        case RCU_SCHED_FLAVOR:
                rsp = &rcu_sched_state;
                break;
@@ -2918,18 +2951,17 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 /*
  * Do RCU core processing for the current CPU.
  */
-static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
+static __latent_entropy void rcu_process_callbacks(void)
 {
        struct rcu_state *rsp;
 
        if (cpu_is_offline(smp_processor_id()))
                return;
-       trace_rcu_utilization(TPS("Start RCU core"));
        for_each_rcu_flavor(rsp)
                __rcu_process_callbacks(rsp);
-       trace_rcu_utilization(TPS("End RCU core"));
 }
 
+static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 /*
  * Schedule RCU callback invocation.  If the specified type of RCU
  * does not support RCU priority boosting, just do a direct call,
@@ -2941,19 +2973,106 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
        if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
                return;
-       if (likely(!rsp->boost)) {
-               rcu_do_batch(rsp, rdp);
-               return;
-       }
-       invoke_rcu_callbacks_kthread();
+       rcu_do_batch(rsp, rdp);
 }
 
+static void rcu_wake_cond(struct task_struct *t, int status)
+{
+       /*
+        * If the thread is yielding, only wake it when this
+        * is invoked from idle
+        */
+       if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
+               wake_up_process(t);
+}
+
+/*
+ * Wake up this CPU's rcuc kthread to do RCU core processing.
+ */
 static void invoke_rcu_core(void)
 {
-       if (cpu_online(smp_processor_id()))
-               raise_softirq(RCU_SOFTIRQ);
+       unsigned long flags;
+       struct task_struct *t;
+
+       if (!cpu_online(smp_processor_id()))
+               return;
+       local_irq_save(flags);
+       __this_cpu_write(rcu_cpu_has_work, 1);
+       t = __this_cpu_read(rcu_cpu_kthread_task);
+       if (t != NULL && current != t)
+               rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status));
+       local_irq_restore(flags);
+}
+
+static void rcu_cpu_kthread_park(unsigned int cpu)
+{
+       per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+}
+
+static int rcu_cpu_kthread_should_run(unsigned int cpu)
+{
+       return __this_cpu_read(rcu_cpu_has_work);
 }
 
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
+ * RCU softirq used in flavors and configurations of RCU that do not
+ * support RCU priority boosting.
+ */
+static void rcu_cpu_kthread(unsigned int cpu)
+{
+       unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
+       char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
+       int spincnt;
+
+       for (spincnt = 0; spincnt < 10; spincnt++) {
+               trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
+               local_bh_disable();
+               *statusp = RCU_KTHREAD_RUNNING;
+               this_cpu_inc(rcu_cpu_kthread_loops);
+               local_irq_disable();
+               work = *workp;
+               *workp = 0;
+               local_irq_enable();
+               if (work)
+                       rcu_process_callbacks();
+               local_bh_enable();
+               if (*workp == 0) {
+                       trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
+                       *statusp = RCU_KTHREAD_WAITING;
+                       return;
+               }
+       }
+       *statusp = RCU_KTHREAD_YIELDING;
+       trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
+       schedule_timeout_interruptible(2);
+       trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
+       *statusp = RCU_KTHREAD_WAITING;
+}
+
+static struct smp_hotplug_thread rcu_cpu_thread_spec = {
+       .store                  = &rcu_cpu_kthread_task,
+       .thread_should_run      = rcu_cpu_kthread_should_run,
+       .thread_fn              = rcu_cpu_kthread,
+       .thread_comm            = "rcuc/%u",
+       .setup                  = rcu_cpu_kthread_setup,
+       .park                   = rcu_cpu_kthread_park,
+};
+
+/*
+ * Spawn per-CPU RCU core processing kthreads.
+ */
+static int __init rcu_spawn_core_kthreads(void)
+{
+       int cpu;
+
+       for_each_possible_cpu(cpu)
+               per_cpu(rcu_cpu_has_work, cpu) = 0;
+       BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
+       return 0;
+}
+early_initcall(rcu_spawn_core_kthreads);
+
 /*
  * Handle any core-RCU processing required by a call_rcu() invocation.
  */
@@ -3113,6 +3232,7 @@ void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
 }
 EXPORT_SYMBOL_GPL(call_rcu_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -3140,6 +3260,7 @@ void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
        __call_rcu(head, func, &rcu_bh_state, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
+#endif
 
 /*
  * Queue an RCU callback for lazy invocation after a grace period.
@@ -3225,6 +3346,7 @@ void synchronize_sched(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
  *
@@ -3251,6 +3373,7 @@ void synchronize_rcu_bh(void)
                wait_rcu_gp(call_rcu_bh);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+#endif
 
 /**
  * get_state_synchronize_rcu - Snapshot current RCU state
@@ -3601,6 +3724,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
        mutex_unlock(&rsp->barrier_mutex);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
  */
@@ -3609,6 +3733,7 @@ void rcu_barrier_bh(void)
        _rcu_barrier(&rcu_bh_state);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+#endif
 
 /**
  * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
@@ -3741,8 +3866,6 @@ int rcutree_online_cpu(unsigned int cpu)
 {
        sync_sched_exp_online_cleanup(cpu);
        rcutree_affinity_setting(cpu, -1);
-       if (IS_ENABLED(CONFIG_TREE_SRCU))
-               srcu_online_cpu(cpu);
        return 0;
 }
 
@@ -3753,8 +3876,6 @@ int rcutree_online_cpu(unsigned int cpu)
 int rcutree_offline_cpu(unsigned int cpu)
 {
        rcutree_affinity_setting(cpu, cpu);
-       if (IS_ENABLED(CONFIG_TREE_SRCU))
-               srcu_offline_cpu(cpu);
        return 0;
 }
 
@@ -4184,12 +4305,13 @@ void __init rcu_init(void)
 
        rcu_bootup_announce();
        rcu_init_geometry();
+#ifndef CONFIG_PREEMPT_RT_FULL
        rcu_init_one(&rcu_bh_state);
+#endif
        rcu_init_one(&rcu_sched_state);
        if (dump_tree)
                rcu_dump_rcu_node_tree(&rcu_sched_state);
        __rcu_init_preempt();
-       open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
        /*
         * We don't need protection against CPU-hotplug here because
@@ -4200,8 +4322,6 @@ void __init rcu_init(void)
        for_each_online_cpu(cpu) {
                rcutree_prepare_cpu(cpu);
                rcu_cpu_starting(cpu);
-               if (IS_ENABLED(CONFIG_TREE_SRCU))
-                       srcu_online_cpu(cpu);
        }
 }
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8e1f285f0a70..7acc23da94e2 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -427,7 +427,9 @@ extern struct list_head rcu_struct_flavors;
  */
 extern struct rcu_state rcu_sched_state;
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern struct rcu_state rcu_bh_state;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
@@ -436,12 +438,10 @@ extern struct rcu_state rcu_preempt_state;
 int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
 bool rcu_eqs_special_set(int cpu);
 
-#ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
 DECLARE_PER_CPU(char, rcu_cpu_has_work);
-#endif /* #ifdef CONFIG_RCU_BOOST */
 
 #ifndef RCU_TREE_NONCORE
 
@@ -461,10 +461,9 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
-static void invoke_rcu_callbacks_kthread(void);
 static bool rcu_is_callbacks_kthread(void);
+static void rcu_cpu_kthread_setup(unsigned int cpu);
 #ifdef CONFIG_RCU_BOOST
-static void rcu_preempt_do_callbacks(void);
 static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
                                                 struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 8b3102d22823..17ee8d1f38c4 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -24,39 +24,16 @@
  *        Paul E. McKenney <paulmck@linux.vnet.ibm.com>
  */
 
-#include <linux/delay.h>
-#include <linux/gfp.h>
-#include <linux/oom.h>
-#include <linux/sched/debug.h>
-#include <linux/smpboot.h>
-#include <uapi/linux/sched/types.h>
-#include "../time/tick-internal.h"
-
-#ifdef CONFIG_RCU_BOOST
-
 #include "../locking/rtmutex_common.h"
 
 /*
  * Control variables for per-CPU and per-rcu_node kthreads.  These
  * handle all flavors of RCU.
  */
-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 
-#else /* #ifdef CONFIG_RCU_BOOST */
-
-/*
- * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
- * all uses are in dead code.  Provide a definition to keep the compiler
- * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
- * This probably needs to be excluded from -rt builds.
- */
-#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
-
-#endif /* #else #ifdef CONFIG_RCU_BOOST */
-
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
 static bool have_rcu_nocb_mask;            /* Was rcu_nocb_mask allocated? */
@@ -324,9 +301,13 @@ static void rcu_preempt_note_context_switch(bool preempt)
        struct task_struct *t = current;
        struct rcu_data *rdp;
        struct rcu_node *rnp;
+       int sleeping_l = 0;
 
        RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_preempt_note_context_switch() invoked with interrupts enabled!!!\n");
-       WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0);
+#if defined(CONFIG_PREEMPT_RT_FULL)
+       sleeping_l = t->sleeping_lock;
+#endif
+       WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0 && !sleeping_l);
        if (t->rcu_read_lock_nesting > 0 &&
            !t->rcu_read_unlock_special.b.blocked) {
 
@@ -463,7 +444,7 @@ void rcu_read_unlock_special(struct task_struct *t)
        }
 
        /* Hardware IRQ handlers cannot block, complain if they get here. */
-       if (in_irq() || in_serving_softirq()) {
+       if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) {
                lockdep_rcu_suspicious(__FILE__, __LINE__,
                                       "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n");
                pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n",
@@ -530,7 +511,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 
                /* Unboost if we were boosted. */
                if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
-                       rt_mutex_unlock(&rnp->boost_mtx);
+                       rt_mutex_futex_unlock(&rnp->boost_mtx);
 
                /*
                 * If this was the last task on the expedited lists,
@@ -684,15 +665,6 @@ static void rcu_preempt_check_callbacks(void)
                t->rcu_read_unlock_special.b.need_qs = true;
 }
 
-#ifdef CONFIG_RCU_BOOST
-
-static void rcu_preempt_do_callbacks(void)
-{
-       rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
-}
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
 /**
  * call_rcu() - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -915,20 +887,23 @@ void exit_rcu(void)
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+/*
+ * If boosting, set rcuc kthreads to realtime priority.
+ */
+static void rcu_cpu_kthread_setup(unsigned int cpu)
+{
+#ifdef CONFIG_RCU_BOOST
+       struct sched_param sp;
+
+       sp.sched_priority = kthread_prio;
+       sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+}
+
 #ifdef CONFIG_RCU_BOOST
 
 #include "../locking/rtmutex_common.h"
 
-static void rcu_wake_cond(struct task_struct *t, int status)
-{
-       /*
-        * If the thread is yielding, only wake it when this
-        * is invoked from idle
-        */
-       if (status != RCU_KTHREAD_YIELDING || is_idle_task(current))
-               wake_up_process(t);
-}
-
 /*
  * Carry out RCU priority boosting on the task indicated by ->exp_tasks
  * or ->boost_tasks, advancing the pointer to the next task in the
@@ -1070,23 +1045,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
        }
 }
 
-/*
- * Wake up the per-CPU kthread to invoke RCU callbacks.
- */
-static void invoke_rcu_callbacks_kthread(void)
-{
-       unsigned long flags;
-
-       local_irq_save(flags);
-       __this_cpu_write(rcu_cpu_has_work, 1);
-       if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
-           current != __this_cpu_read(rcu_cpu_kthread_task)) {
-               rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
-                             __this_cpu_read(rcu_cpu_kthread_status));
-       }
-       local_irq_restore(flags);
-}
-
 /*
  * Is the current CPU running the RCU-callbacks kthread?
  * Caller must have preemption disabled.
@@ -1141,67 +1099,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
        return 0;
 }
 
-static void rcu_kthread_do_work(void)
-{
-       rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
-       rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
-       rcu_preempt_do_callbacks();
-}
-
-static void rcu_cpu_kthread_setup(unsigned int cpu)
-{
-       struct sched_param sp;
-
-       sp.sched_priority = kthread_prio;
-       sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
-}
-
-static void rcu_cpu_kthread_park(unsigned int cpu)
-{
-       per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
-}
-
-static int rcu_cpu_kthread_should_run(unsigned int cpu)
-{
-       return __this_cpu_read(rcu_cpu_has_work);
-}
-
-/*
- * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
- * RCU softirq used in flavors and configurations of RCU that do not
- * support RCU priority boosting.
- */
-static void rcu_cpu_kthread(unsigned int cpu)
-{
-       unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
-       char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
-       int spincnt;
-
-       for (spincnt = 0; spincnt < 10; spincnt++) {
-               trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
-               local_bh_disable();
-               *statusp = RCU_KTHREAD_RUNNING;
-               this_cpu_inc(rcu_cpu_kthread_loops);
-               local_irq_disable();
-               work = *workp;
-               *workp = 0;
-               local_irq_enable();
-               if (work)
-                       rcu_kthread_do_work();
-               local_bh_enable();
-               if (*workp == 0) {
-                       trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
-                       *statusp = RCU_KTHREAD_WAITING;
-                       return;
-               }
-       }
-       *statusp = RCU_KTHREAD_YIELDING;
-       trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
-       schedule_timeout_interruptible(2);
-       trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
-       *statusp = RCU_KTHREAD_WAITING;
-}
-
 /*
  * Set the per-rcu_node kthread's affinity to cover all CPUs that are
  * served by the rcu_node in question.  The CPU hotplug lock is still
@@ -1232,26 +1129,12 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
        free_cpumask_var(cm);
 }
 
-static struct smp_hotplug_thread rcu_cpu_thread_spec = {
-       .store                  = &rcu_cpu_kthread_task,
-       .thread_should_run      = rcu_cpu_kthread_should_run,
-       .thread_fn              = rcu_cpu_kthread,
-       .thread_comm            = "rcuc/%u",
-       .setup                  = rcu_cpu_kthread_setup,
-       .park                   = rcu_cpu_kthread_park,
-};
-
 /*
  * Spawn boost kthreads -- called as soon as the scheduler is running.
  */
 static void __init rcu_spawn_boost_kthreads(void)
 {
        struct rcu_node *rnp;
-       int cpu;
-
-       for_each_possible_cpu(cpu)
-               per_cpu(rcu_cpu_has_work, cpu) = 0;
-       BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
        rcu_for_each_leaf_node(rcu_state_p, rnp)
                (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
 }
@@ -1274,11 +1157,6 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
        raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
-static void invoke_rcu_callbacks_kthread(void)
-{
-       WARN_ON_ONCE(1);
-}
-
 static bool rcu_is_callbacks_kthread(void)
 {
        return false;
@@ -1302,7 +1180,7 @@ static void rcu_prepare_kthreads(int cpu)
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
-#if !defined(CONFIG_RCU_FAST_NO_HZ)
+#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL)
 
 /*
  * Check to see if any future RCU-related work will need to be done
@@ -1318,7 +1196,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
        *nextevt = KTIME_MAX;
        return rcu_cpu_has_callbacks(NULL);
 }
+#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */
 
+#if !defined(CONFIG_RCU_FAST_NO_HZ)
 /*
  * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
  * after it.
@@ -1414,6 +1294,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
        return cbs_ready;
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
  * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
@@ -1456,6 +1338,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
        *nextevt = basemono + dj * TICK_NSEC;
        return 0;
 }
+#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */
 
 /*
  * Prepare a CPU for idle from an RCU perspective.  The first major task
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 7a577bd989a4..2006a09680aa 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -66,7 +66,7 @@ extern int rcu_expedited; /* from sysctl */
 module_param(rcu_expedited, int, 0);
 extern int rcu_normal; /* from sysctl */
 module_param(rcu_normal, int, 0);
-static int rcu_normal_after_boot;
+static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL);
 module_param(rcu_normal_after_boot, int, 0);
 #endif /* #ifndef CONFIG_TINY_RCU */
 
@@ -333,6 +333,7 @@ int rcu_read_lock_held(void)
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_held);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
@@ -359,6 +360,7 @@ int rcu_read_lock_bh_held(void)
        return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
+#endif
 
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index a9ee16bbc693..9943019095e9 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,7 +18,7 @@ endif
 
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o
-obj-y += wait.o wait_bit.o swait.o completion.o idle.o
+obj-y += wait.o wait_bit.o swait.o swork.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 2ddaec40956f..0fe2982e46a0 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -32,7 +32,7 @@ void complete(struct completion *x)
 {
        unsigned long flags;
 
-       spin_lock_irqsave(&x->wait.lock, flags);
+       raw_spin_lock_irqsave(&x->wait.lock, flags);
 
        /*
         * Perform commit of crossrelease here.
@@ -41,8 +41,8 @@ void complete(struct completion *x)
 
        if (x->done != UINT_MAX)
                x->done++;
-       __wake_up_locked(&x->wait, TASK_NORMAL, 1);
-       spin_unlock_irqrestore(&x->wait.lock, flags);
+       swake_up_locked(&x->wait);
+       raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete);
 
@@ -66,10 +66,10 @@ void complete_all(struct completion *x)
 {
        unsigned long flags;
 
-       spin_lock_irqsave(&x->wait.lock, flags);
+       raw_spin_lock_irqsave(&x->wait.lock, flags);
        x->done = UINT_MAX;
-       __wake_up_locked(&x->wait, TASK_NORMAL, 0);
-       spin_unlock_irqrestore(&x->wait.lock, flags);
+       swake_up_all_locked(&x->wait);
+       raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete_all);
 
@@ -78,20 +78,20 @@ do_wait_for_common(struct completion *x,
                   long (*action)(long), long timeout, int state)
 {
        if (!x->done) {
-               DECLARE_WAITQUEUE(wait, current);
+               DECLARE_SWAITQUEUE(wait);
 
-               __add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
+               __prepare_to_swait(&x->wait, &wait);
                do {
                        if (signal_pending_state(state, current)) {
                                timeout = -ERESTARTSYS;
                                break;
                        }
                        __set_current_state(state);
-                       spin_unlock_irq(&x->wait.lock);
+                       raw_spin_unlock_irq(&x->wait.lock);
                        timeout = action(timeout);
-                       spin_lock_irq(&x->wait.lock);
+                       raw_spin_lock_irq(&x->wait.lock);
                } while (!x->done && timeout);
-               __remove_wait_queue(&x->wait, &wait);
+               __finish_swait(&x->wait, &wait);
                if (!x->done)
                        return timeout;
        }
@@ -108,9 +108,9 @@ __wait_for_common(struct completion *x,
 
        complete_acquire(x);
 
-       spin_lock_irq(&x->wait.lock);
+       raw_spin_lock_irq(&x->wait.lock);
        timeout = do_wait_for_common(x, action, timeout, state);
-       spin_unlock_irq(&x->wait.lock);
+       raw_spin_unlock_irq(&x->wait.lock);
 
        complete_release(x);
 
@@ -299,12 +299,12 @@ bool try_wait_for_completion(struct completion *x)
        if (!READ_ONCE(x->done))
                return 0;
 
-       spin_lock_irqsave(&x->wait.lock, flags);
+       raw_spin_lock_irqsave(&x->wait.lock, flags);
        if (!x->done)
                ret = 0;
        else if (x->done != UINT_MAX)
                x->done--;
-       spin_unlock_irqrestore(&x->wait.lock, flags);
+       raw_spin_unlock_irqrestore(&x->wait.lock, flags);
        return ret;
 }
 EXPORT_SYMBOL(try_wait_for_completion);
@@ -330,8 +330,8 @@ bool completion_done(struct completion *x)
         * otherwise we can end up freeing the completion before complete()
         * is done referencing it.
         */
-       spin_lock_irqsave(&x->wait.lock, flags);
-       spin_unlock_irqrestore(&x->wait.lock, flags);
+       raw_spin_lock_irqsave(&x->wait.lock, flags);
+       raw_spin_unlock_irqrestore(&x->wait.lock, flags);
        return true;
 }
 EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4e89ed8a0fb2..6e6bd5262f23 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -59,7 +59,11 @@ const_debug unsigned int sysctl_sched_features =
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
+#else
+const_debug unsigned int sysctl_sched_nr_migrate = 8;
+#endif
 
 /*
  * period over which we average the RT time consumption, measured
@@ -341,7 +345,7 @@ static void init_rq_hrtick(struct rq *rq)
        rq->hrtick_csd.info = rq;
 #endif
 
-       hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
        rq->hrtick_timer.function = hrtick;
 }
 #else  /* CONFIG_SCHED_HRTICK */
@@ -423,9 +427,15 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
-void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+void __wake_q_add(struct wake_q_head *head, struct task_struct *task,
+                 bool sleeper)
 {
-       struct wake_q_node *node = &task->wake_q;
+       struct wake_q_node *node;
+
+       if (sleeper)
+               node = &task->wake_q_sleeper;
+       else
+               node = &task->wake_q;
 
        /*
         * Atomically grab the task, if ->wake_q is !nil already it means
@@ -447,24 +457,32 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
        head->lastp = &node->next;
 }
 
-void wake_up_q(struct wake_q_head *head)
+void __wake_up_q(struct wake_q_head *head, bool sleeper)
 {
        struct wake_q_node *node = head->first;
 
        while (node != WAKE_Q_TAIL) {
                struct task_struct *task;
 
-               task = container_of(node, struct task_struct, wake_q);
+               if (sleeper)
+                       task = container_of(node, struct task_struct, wake_q_sleeper);
+               else
+                       task = container_of(node, struct task_struct, wake_q);
                BUG_ON(!task);
                /* Task can safely be re-inserted now: */
                node = node->next;
-               task->wake_q.next = NULL;
-
+               if (sleeper)
+                       task->wake_q_sleeper.next = NULL;
+               else
+                       task->wake_q.next = NULL;
                /*
                 * wake_up_process() implies a wmb() to pair with the queueing
                 * in wake_q_add() so as not to miss wakeups.
                 */
-               wake_up_process(task);
+               if (sleeper)
+                       wake_up_lock_sleeper(task);
+               else
+                       wake_up_process(task);
                put_task_struct(task);
        }
 }
@@ -500,6 +518,48 @@ void resched_curr(struct rq *rq)
                trace_sched_wake_idle_without_ipi(cpu);
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+
+static int tsk_is_polling(struct task_struct *p)
+{
+#ifdef TIF_POLLING_NRFLAG
+       return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
+#else
+       return 0;
+#endif
+}
+
+void resched_curr_lazy(struct rq *rq)
+{
+       struct task_struct *curr = rq->curr;
+       int cpu;
+
+       if (!sched_feat(PREEMPT_LAZY)) {
+               resched_curr(rq);
+               return;
+       }
+
+       lockdep_assert_held(&rq->lock);
+
+       if (test_tsk_need_resched(curr))
+               return;
+
+       if (test_tsk_need_resched_lazy(curr))
+               return;
+
+       set_tsk_need_resched_lazy(curr);
+
+       cpu = cpu_of(rq);
+       if (cpu == smp_processor_id())
+               return;
+
+       /* NEED_RESCHED_LAZY must be visible before we test polling */
+       smp_mb();
+       if (!tsk_is_polling(curr))
+               smp_send_reschedule(cpu);
+}
+#endif
+
 void resched_cpu(int cpu)
 {
        struct rq *rq = cpu_rq(cpu);
@@ -523,11 +583,14 @@ void resched_cpu(int cpu)
  */
 int get_nohz_timer_target(void)
 {
-       int i, cpu = smp_processor_id();
+       int i, cpu;
        struct sched_domain *sd;
 
+       preempt_disable_rt();
+       cpu = smp_processor_id();
+
        if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
-               return cpu;
+               goto preempt_en_rt;
 
        rcu_read_lock();
        for_each_domain(cpu, sd) {
@@ -546,6 +609,8 @@ int get_nohz_timer_target(void)
                cpu = housekeeping_any_cpu();
 unlock:
        rcu_read_unlock();
+preempt_en_rt:
+       preempt_enable_rt();
        return cpu;
 }
 
@@ -912,10 +977,10 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 {
-       if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+       if (!cpumask_test_cpu(cpu, p->cpus_ptr))
                return false;
 
-       if (is_per_cpu_kthread(p))
+       if (is_per_cpu_kthread(p) || __migrate_disabled(p))
                return cpu_online(cpu);
 
        return cpu_active(cpu);
@@ -1007,7 +1072,7 @@ static int migration_cpu_stop(void *data)
        local_irq_disable();
        /*
         * We need to explicitly wake pending tasks before running
-        * __migrate_task() such that we will not miss enforcing cpus_allowed
+        * __migrate_task() such that we will not miss enforcing cpus_ptr
         * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
         */
        sched_ttwu_pending();
@@ -1038,11 +1103,19 @@ static int migration_cpu_stop(void *data)
  */
 void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
 {
-       cpumask_copy(&p->cpus_allowed, new_mask);
+       cpumask_copy(&p->cpus_mask, new_mask);
        p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+int __migrate_disabled(struct task_struct *p)
+{
+       return p->migrate_disable;
+}
+#endif
+
+static void __do_set_cpus_allowed_tail(struct task_struct *p,
+                                      const struct cpumask *new_mask)
 {
        struct rq *rq = task_rq(p);
        bool queued, running;
@@ -1071,6 +1144,20 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
                set_curr_task(rq, p);
 }
 
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+       if (__migrate_disabled(p)) {
+               lockdep_assert_held(&p->pi_lock);
+
+               cpumask_copy(&p->cpus_mask, new_mask);
+               p->migrate_disable_update = 1;
+               return;
+       }
+#endif
+       __do_set_cpus_allowed_tail(p, new_mask);
+}
+
 /*
  * Change a given task's CPU affinity. Migrate the thread to a
  * proper CPU and schedule it away if the CPU it's executing on
@@ -1108,7 +1195,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
                goto out;
        }
 
-       if (cpumask_equal(&p->cpus_allowed, new_mask))
+       if (cpumask_equal(p->cpus_ptr, new_mask))
                goto out;
 
        if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
@@ -1129,9 +1216,16 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
        }
 
        /* Can the task run on the task's current CPU? If so, we're done */
-       if (cpumask_test_cpu(task_cpu(p), new_mask))
+       if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p))
                goto out;
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+       if (__migrate_disabled(p)) {
+               p->migrate_disable_update = 1;
+               goto out;
+       }
+#endif
+
        dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
        if (task_running(rq, p) || p->state == TASK_WAKING) {
                struct migration_arg arg = { p, dest_cpu };
@@ -1269,10 +1363,10 @@ static int migrate_swap_stop(void *data)
        if (task_cpu(arg->src_task) != arg->src_cpu)
                goto unlock;
 
-       if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
+       if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr))
                goto unlock;
 
-       if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
+       if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr))
                goto unlock;
 
        __migrate_swap_task(arg->src_task, arg->dst_cpu);
@@ -1313,10 +1407,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
        if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
                goto out;
 
-       if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
+       if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr))
                goto out;
 
-       if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
+       if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr))
                goto out;
 
        trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
@@ -1326,6 +1420,18 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
        return ret;
 }
 
+static bool check_task_state(struct task_struct *p, long match_state)
+{
+       bool match = false;
+
+       raw_spin_lock_irq(&p->pi_lock);
+       if (p->state == match_state || p->saved_state == match_state)
+               match = true;
+       raw_spin_unlock_irq(&p->pi_lock);
+
+       return match;
+}
+
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
@@ -1370,7 +1476,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
                 * is actually now running somewhere else!
                 */
                while (task_running(rq, p)) {
-                       if (match_state && unlikely(p->state != match_state))
+                       if (match_state && !check_task_state(p, match_state))
                                return 0;
                        cpu_relax();
                }
@@ -1385,7 +1491,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
                running = task_running(rq, p);
                queued = task_on_rq_queued(p);
                ncsw = 0;
-               if (!match_state || p->state == match_state)
+               if (!match_state || p->state == match_state ||
+                   p->saved_state == match_state)
                        ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
                task_rq_unlock(rq, p, &rf);
 
@@ -1460,7 +1567,7 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 
 /*
- * ->cpus_allowed is protected by both rq->lock and p->pi_lock
+ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
  *
  * A few notes on cpu_active vs cpu_online:
  *
@@ -1500,14 +1607,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
                for_each_cpu(dest_cpu, nodemask) {
                        if (!cpu_active(dest_cpu))
                                continue;
-                       if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+                       if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
                                return dest_cpu;
                }
        }
 
        for (;;) {
                /* Any allowed, online CPU? */
-               for_each_cpu(dest_cpu, &p->cpus_allowed) {
+               for_each_cpu(dest_cpu, p->cpus_ptr) {
                        if (!is_cpu_allowed(p, dest_cpu))
                                continue;
 
@@ -1551,7 +1658,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
  */
 static inline
 int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
@@ -1561,11 +1668,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
        if (p->nr_cpus_allowed > 1)
                cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
        else
-               cpu = cpumask_any(&p->cpus_allowed);
+               cpu = cpumask_any(p->cpus_ptr);
 
        /*
         * In order not to call set_task_cpu() on a blocking task we need
-        * to rely on ttwu() to place the task on a valid ->cpus_allowed
+        * to rely on ttwu() to place the task on a valid ->cpus_ptr
         * CPU.
         *
         * Since this is common to all placement strategies, this lives here.
@@ -1668,10 +1775,6 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
 {
        activate_task(rq, p, en_flags);
        p->on_rq = TASK_ON_RQ_QUEUED;
-
-       /* If a worker is waking up, notify the workqueue: */
-       if (p->flags & PF_WQ_WORKER)
-               wq_worker_waking_up(p, cpu_of(rq));
 }
 
 /*
@@ -1995,8 +2098,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
         */
        raw_spin_lock_irqsave(&p->pi_lock, flags);
        smp_mb__after_spinlock();
-       if (!(p->state & state))
+       if (!(p->state & state)) {
+               /*
+                * The task might be running due to a spinlock sleeper
+                * wakeup. Check the saved state and set it to running
+                * if the wakeup condition is true.
+                */
+               if (!(wake_flags & WF_LOCK_SLEEPER)) {
+                       if (p->saved_state & state) {
+                               p->saved_state = TASK_RUNNING;
+                               success = 1;
+                       }
+               }
                goto out;
+       }
+
+       /*
+        * If this is a regular wakeup, then we can unconditionally
+        * clear the saved state of a "lock sleeper".
+        */
+       if (!(wake_flags & WF_LOCK_SLEEPER))
+               p->saved_state = TASK_RUNNING;
 
        trace_sched_waking(p);
 
@@ -2092,56 +2214,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
        return success;
 }
 
-/**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
-       struct rq *rq = task_rq(p);
-
-       if (WARN_ON_ONCE(rq != this_rq()) ||
-           WARN_ON_ONCE(p == current))
-               return;
-
-       lockdep_assert_held(&rq->lock);
-
-       if (!raw_spin_trylock(&p->pi_lock)) {
-               /*
-                * This is OK, because current is on_cpu, which avoids it being
-                * picked for load-balance and preemption/IRQs are still
-                * disabled avoiding further scheduler activity on it and we've
-                * not yet picked a replacement task.
-                */
-               rq_unlock(rq, rf);
-               raw_spin_lock(&p->pi_lock);
-               rq_relock(rq, rf);
-       }
-
-       if (!(p->state & TASK_NORMAL))
-               goto out;
-
-       trace_sched_waking(p);
-
-       if (!task_on_rq_queued(p)) {
-               if (p->in_iowait) {
-                       delayacct_blkio_end(p);
-                       atomic_dec(&rq->nr_iowait);
-               }
-               ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
-       }
-
-       ttwu_do_wakeup(rq, p, 0, rf);
-       ttwu_stat(p, smp_processor_id(), 0);
-out:
-       raw_spin_unlock(&p->pi_lock);
-}
-
 /**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
@@ -2160,6 +2232,18 @@ int wake_up_process(struct task_struct *p)
 }
 EXPORT_SYMBOL(wake_up_process);
 
+/**
+ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock"
+ * @p: The process to be woken up.
+ *
+ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate
+ * the nature of the wakeup.
+ */
+int wake_up_lock_sleeper(struct task_struct *p)
+{
+       return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER);
+}
+
 int wake_up_state(struct task_struct *p, unsigned int state)
 {
        return try_to_wake_up(p, state, 0);
@@ -2420,6 +2504,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
        p->on_cpu = 0;
 #endif
        init_task_preempt_count(p);
+#ifdef CONFIG_HAVE_PREEMPT_LAZY
+       task_thread_info(p)->preempt_lazy_count = 0;
+#endif
 #ifdef CONFIG_SMP
        plist_node_init(&p->pushable_tasks, MAX_PRIO);
        RB_CLEAR_NODE(&p->pushable_dl_tasks);
@@ -2462,7 +2549,7 @@ void wake_up_new_task(struct task_struct *p)
 #ifdef CONFIG_SMP
        /*
         * Fork balancing, do it here and not earlier because:
-        *  - cpus_allowed can change in the fork path
+        *  - cpus_ptr can change in the fork path
         *  - any previously selected CPU might disappear through hotplug
         *
         * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
@@ -2675,21 +2762,16 @@ static struct rq *finish_task_switch(struct task_struct *prev)
        finish_arch_post_lock_switch();
 
        fire_sched_in_preempt_notifiers(current);
+       /*
+        * We use mmdrop_delayed() here so we don't have to do the
+        * full __mmdrop() when we are the last user.
+        */
        if (mm)
-               mmdrop(mm);
+               mmdrop_delayed(mm);
        if (unlikely(prev_state == TASK_DEAD)) {
                if (prev->sched_class->task_dead)
                        prev->sched_class->task_dead(prev);
 
-               /*
-                * Remove function-return probe instances associated with this
-                * task and put them back on the free list.
-                */
-               kprobe_flush_task(prev);
-
-               /* Task is done with its stack. */
-               put_task_stack(prev);
-
                put_task_struct(prev);
        }
 
@@ -3336,25 +3418,13 @@ static void __sched notrace __schedule(bool preempt)
                                atomic_inc(&rq->nr_iowait);
                                delayacct_blkio_start();
                        }
-
-                       /*
-                        * If a worker went to sleep, notify and ask workqueue
-                        * whether it wants to wake up a task to maintain
-                        * concurrency.
-                        */
-                       if (prev->flags & PF_WQ_WORKER) {
-                               struct task_struct *to_wakeup;
-
-                               to_wakeup = wq_worker_sleeping(prev);
-                               if (to_wakeup)
-                                       try_to_wake_up_local(to_wakeup, &rf);
-                       }
                }
                switch_count = &prev->nvcsw;
        }
 
        next = pick_next_task(rq, prev, &rf);
        clear_tsk_need_resched(prev);
+       clear_tsk_need_resched_lazy(prev);
        clear_preempt_need_resched();
 
        if (likely(prev != next)) {
@@ -3407,8 +3477,24 @@ void __noreturn do_task_dead(void)
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
-       if (!tsk->state || tsk_is_pi_blocked(tsk))
+       if (!tsk->state)
                return;
+       /*
+        * If a worker went to sleep, notify and ask workqueue whether
+        * it wants to wake up a task to maintain concurrency.
+        * As this function is called inside the schedule() context,
+        * we disable preemption to avoid it calling schedule() again
+        * in the possible wakeup of a kworker.
+        */
+       if (tsk->flags & PF_WQ_WORKER) {
+               preempt_disable();
+               wq_worker_sleeping(tsk);
+               preempt_enable_no_resched();
+       }
+
+       if (tsk_is_pi_blocked(tsk))
+               return;
+
        /*
         * If we are going to sleep and we have plugged IO queued,
         * make sure to submit it to avoid deadlocks.
@@ -3417,6 +3503,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
                blk_schedule_flush_plug(tsk);
 }
 
+static void sched_update_worker(struct task_struct *tsk)
+{
+       if (tsk->flags & PF_WQ_WORKER)
+               wq_worker_running(tsk);
+}
+
 asmlinkage __visible void __sched schedule(void)
 {
        struct task_struct *tsk = current;
@@ -3427,6 +3519,7 @@ asmlinkage __visible void __sched schedule(void)
                __schedule(false);
                sched_preempt_enable_no_resched();
        } while (need_resched());
+       sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
@@ -3515,6 +3608,30 @@ static void __sched notrace preempt_schedule_common(void)
        } while (need_resched());
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+/*
+ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is
+ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as
+ * preempt_lazy_count counter >0.
+ */
+static __always_inline int preemptible_lazy(void)
+{
+       if (test_thread_flag(TIF_NEED_RESCHED))
+               return 1;
+       if (current_thread_info()->preempt_lazy_count)
+               return 0;
+       return 1;
+}
+
+#else
+
+static inline int preemptible_lazy(void)
+{
+       return 1;
+}
+
+#endif
+
 #ifdef CONFIG_PREEMPT
 /*
  * this is the entry point to schedule() from in-kernel preemption
@@ -3529,7 +3646,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
         */
        if (likely(!preemptible()))
                return;
-
+       if (!preemptible_lazy())
+               return;
        preempt_schedule_common();
 }
 NOKPROBE_SYMBOL(preempt_schedule);
@@ -3556,6 +3674,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
        if (likely(!preemptible()))
                return;
 
+       if (!preemptible_lazy())
+               return;
+
        do {
                /*
                 * Because the function tracer can trace preempt_count_sub()
@@ -3578,7 +3699,16 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
                 * an infinite recursion.
                 */
                prev_ctx = exception_enter();
+               /*
+                * The add/subtract must not be traced by the function
+                * tracer. But we still want to account for the
+                * preempt off latency tracer. Since the _notrace versions
+                * of add/subtract skip the accounting for latency tracer
+                * we must force it manually.
+                */
+               start_critical_timings();
                __schedule(true);
+               stop_critical_timings();
                exception_exit(prev_ctx);
 
                preempt_latency_stop(1);
@@ -4164,7 +4294,7 @@ static int __sched_setscheduler(struct task_struct *p,
                         * the entire root_domain to become SCHED_DEADLINE. We
                         * will also fail if there's no bandwidth available.
                         */
-                       if (!cpumask_subset(span, &p->cpus_allowed) ||
+                       if (!cpumask_subset(span, p->cpus_ptr) ||
                            rq->rd->dl_bw.bw == 0) {
                                task_rq_unlock(rq, p, &rf);
                                return -EPERM;
@@ -4758,7 +4888,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
                goto out_unlock;
 
        raw_spin_lock_irqsave(&p->pi_lock, flags);
-       cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
+       cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
@@ -4877,6 +5007,7 @@ int __cond_resched_lock(spinlock_t *lock)
 }
 EXPORT_SYMBOL(__cond_resched_lock);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 int __sched __cond_resched_softirq(void)
 {
        BUG_ON(!in_softirq());
@@ -4890,6 +5021,7 @@ int __sched __cond_resched_softirq(void)
        return 0;
 }
 EXPORT_SYMBOL(__cond_resched_softirq);
+#endif
 
 /**
  * yield - yield the current processor to other threads.
@@ -5284,7 +5416,9 @@ void init_idle(struct task_struct *idle, int cpu)
 
        /* Set the preempt count _outside_ the spinlocks! */
        init_idle_preempt_count(idle, cpu);
-
+#ifdef CONFIG_HAVE_PREEMPT_LAZY
+       task_thread_info(idle)->preempt_lazy_count = 0;
+#endif
        /*
         * The idle tasks have their own, simple scheduling class:
         */
@@ -5323,7 +5457,7 @@ int task_can_attach(struct task_struct *p,
         * allowed nodes is unnecessary.  Thus, cpusets are not
         * applicable for such threads.  This prevents checking for
         * success of set_cpus_allowed_ptr() on all attached tasks
-        * before cpus_allowed may be changed.
+        * before cpus_mask may be changed.
         */
        if (p->flags & PF_NO_SETAFFINITY) {
                ret = -EINVAL;
@@ -5350,7 +5484,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
        if (curr_cpu == target_cpu)
                return 0;
 
-       if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed))
+       if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
                return -EINVAL;
 
        /* TODO: This is not properly updating schedstats */
@@ -5389,6 +5523,8 @@ void sched_setnuma(struct task_struct *p, int nid)
 #endif /* CONFIG_NUMA_BALANCING */
 
 #ifdef CONFIG_HOTPLUG_CPU
+static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm);
+
 /*
  * Ensure that the idle task is using init_mm right before its CPU goes
  * offline.
@@ -5403,7 +5539,12 @@ void idle_task_exit(void)
                switch_mm(mm, &init_mm, current);
                finish_arch_post_lock_switch();
        }
-       mmdrop(mm);
+       /*
+        * Defer the cleanup to an alive cpu. On RT we can neither
+        * call mmdrop() nor mmdrop_delayed() from here.
+        */
+       per_cpu(idle_last_mm, smp_processor_id()) = mm;
+
 }
 
 /*
@@ -5487,7 +5628,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
                put_prev_task(rq, next);
 
                /*
-                * Rules for changing task_struct::cpus_allowed are holding
+                * Rules for changing task_struct::cpus_mask are holding
                 * both pi_lock and rq->lock, such that holding either
                 * stabilizes the mask.
                 *
@@ -5718,6 +5859,10 @@ int sched_cpu_dying(unsigned int cpu)
        update_max_interval();
        nohz_balance_exit_idle(cpu);
        hrtick_clear(rq);
+       if (per_cpu(idle_last_mm, cpu)) {
+               mmdrop_delayed(per_cpu(idle_last_mm, cpu));
+               per_cpu(idle_last_mm, cpu) = NULL;
+       }
        return 0;
 }
 #endif
@@ -5964,7 +6109,7 @@ void __init sched_init(void)
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 static inline int preempt_count_equals(int preempt_offset)
 {
-       int nested = preempt_count() + rcu_preempt_depth();
+       int nested = preempt_count() + sched_rcu_preempt_depth();
 
        return (nested == preempt_offset);
 }
@@ -6756,3 +6901,196 @@ const u32 sched_prio_to_wmult[40] = {
  /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
+
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+
+static inline void
+update_nr_migratory(struct task_struct *p, long delta)
+{
+       if (unlikely((p->sched_class == &rt_sched_class ||
+                     p->sched_class == &dl_sched_class) &&
+                     p->nr_cpus_allowed > 1)) {
+               if (p->sched_class == &rt_sched_class)
+                       task_rq(p)->rt.rt_nr_migratory += delta;
+               else
+                       task_rq(p)->dl.dl_nr_migratory += delta;
+       }
+}
+
+static inline void
+migrate_disable_update_cpus_allowed(struct task_struct *p)
+{
+       struct rq *rq;
+       struct rq_flags rf;
+
+       p->cpus_ptr = cpumask_of(smp_processor_id());
+
+       rq = task_rq_lock(p, &rf);
+       update_nr_migratory(p, -1);
+       p->nr_cpus_allowed = 1;
+       task_rq_unlock(rq, p, &rf);
+}
+
+static inline void
+migrate_enable_update_cpus_allowed(struct task_struct *p)
+{
+       struct rq *rq;
+       struct rq_flags rf;
+
+       p->cpus_ptr = &p->cpus_mask;
+
+       rq = task_rq_lock(p, &rf);
+       p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask);
+       update_nr_migratory(p, 1);
+       task_rq_unlock(rq, p, &rf);
+}
+
+void migrate_disable(void)
+{
+       struct task_struct *p = current;
+
+       if (in_atomic() || irqs_disabled()) {
+#ifdef CONFIG_SCHED_DEBUG
+               p->migrate_disable_atomic++;
+#endif
+               return;
+       }
+#ifdef CONFIG_SCHED_DEBUG
+       if (unlikely(p->migrate_disable_atomic)) {
+               tracing_off();
+               WARN_ON_ONCE(1);
+       }
+#endif
+
+       if (p->migrate_disable) {
+               p->migrate_disable++;
+               return;
+       }
+
+       preempt_disable();
+       preempt_lazy_disable();
+       pin_current_cpu();
+
+       migrate_disable_update_cpus_allowed(p);
+       p->migrate_disable = 1;
+
+       preempt_enable();
+}
+EXPORT_SYMBOL(migrate_disable);
+
+void migrate_enable(void)
+{
+       struct task_struct *p = current;
+
+       if (in_atomic() || irqs_disabled()) {
+#ifdef CONFIG_SCHED_DEBUG
+               p->migrate_disable_atomic--;
+#endif
+               return;
+       }
+
+#ifdef CONFIG_SCHED_DEBUG
+       if (unlikely(p->migrate_disable_atomic)) {
+               tracing_off();
+               WARN_ON_ONCE(1);
+       }
+#endif
+
+       WARN_ON_ONCE(p->migrate_disable <= 0);
+       if (p->migrate_disable > 1) {
+               p->migrate_disable--;
+               return;
+       }
+
+       preempt_disable();
+
+       p->migrate_disable = 0;
+       migrate_enable_update_cpus_allowed(p);
+
+       if (p->migrate_disable_update) {
+               struct rq *rq;
+               struct rq_flags rf;
+
+               rq = task_rq_lock(p, &rf);
+               update_rq_clock(rq);
+
+               __do_set_cpus_allowed_tail(p, &p->cpus_mask);
+               task_rq_unlock(rq, p, &rf);
+
+               p->migrate_disable_update = 0;
+
+               WARN_ON(smp_processor_id() != task_cpu(p));
+               if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
+                       const struct cpumask *cpu_valid_mask = cpu_active_mask;
+                       struct migration_arg arg;
+                       unsigned int dest_cpu;
+
+                       if (p->flags & PF_KTHREAD) {
+                               /*
+                                * Kernel threads are allowed on online && !active CPUs
+                                */
+                               cpu_valid_mask = cpu_online_mask;
+                       }
+                       dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask);
+                       arg.task = p;
+                       arg.dest_cpu = dest_cpu;
+
+                       unpin_current_cpu();
+                       preempt_lazy_enable();
+                       preempt_enable();
+                       stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
+                       tlb_migrate_finish(p->mm);
+
+                       return;
+               }
+       }
+       unpin_current_cpu();
+       preempt_lazy_enable();
+       preempt_enable();
+}
+EXPORT_SYMBOL(migrate_enable);
+
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+void migrate_disable(void)
+{
+#ifdef CONFIG_SCHED_DEBUG
+       struct task_struct *p = current;
+
+       if (in_atomic() || irqs_disabled()) {
+               p->migrate_disable_atomic++;
+               return;
+       }
+
+       if (unlikely(p->migrate_disable_atomic)) {
+               tracing_off();
+               WARN_ON_ONCE(1);
+       }
+
+       p->migrate_disable++;
+#endif
+       barrier();
+}
+EXPORT_SYMBOL(migrate_disable);
+
+void migrate_enable(void)
+{
+#ifdef CONFIG_SCHED_DEBUG
+       struct task_struct *p = current;
+
+       if (in_atomic() || irqs_disabled()) {
+               p->migrate_disable_atomic--;
+               return;
+       }
+
+       if (unlikely(p->migrate_disable_atomic)) {
+               tracing_off();
+               WARN_ON_ONCE(1);
+       }
+
+       WARN_ON_ONCE(p->migrate_disable <= 0);
+       p->migrate_disable--;
+#endif
+       barrier();
+}
+EXPORT_SYMBOL(migrate_enable);
+#endif
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 8d9562d890d3..91a0702fe3df 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -127,13 +127,13 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
        const struct sched_dl_entity *dl_se = &p->dl;
 
        if (later_mask &&
-           cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
+           cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
                return 1;
        } else {
                int best_cpu = cpudl_maximum(cp);
                WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
-               if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) &&
+               if (cpumask_test_cpu(best_cpu, p->cpus_ptr) &&
                    dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
                        if (later_mask)
                                cpumask_set_cpu(best_cpu, later_mask);
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 2511aba36b89..7b9bc1de0e6c 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -103,11 +103,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
                if (skip)
                        continue;
 
-               if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
+               if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
                        continue;
 
                if (lowest_mask) {
-                       cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+                       cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
 
                        /*
                         * We have to ensure that we have at least one bit
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b2589c7e9439..28a75a9526ac 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -504,7 +504,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
                 * If we cannot preempt any rq, fall back to pick any
                 * online cpu.
                 */
-               cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
+               cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr);
                if (cpu >= nr_cpu_ids) {
                        /*
                         * Fail to find any suitable cpu.
@@ -1020,7 +1020,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
        struct hrtimer *timer = &dl_se->dl_timer;
 
-       hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
        timer->function = dl_task_timer;
 }
 
@@ -1753,7 +1753,7 @@ static void set_curr_task_dl(struct rq *rq)
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
        if (!task_running(rq, p) &&
-           cpumask_test_cpu(cpu, &p->cpus_allowed))
+           cpumask_test_cpu(cpu, p->cpus_ptr))
                return 1;
        return 0;
 }
@@ -1903,7 +1903,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
                /* Retry if something changed. */
                if (double_lock_balance(rq, later_rq)) {
                        if (unlikely(task_rq(task) != rq ||
-                                    !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) ||
+                                    !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
                                     task_running(rq, task) ||
                                     !dl_task(task) ||
                                     !task_on_rq_queued(task))) {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2f93e4a2d9f6..b5b43861c2b6 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1017,6 +1017,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
                P(dl.runtime);
                P(dl.deadline);
        }
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+       P(migrate_disable);
+#endif
+       P(nr_cpus_allowed);
 #undef PN_SCHEDSTAT
 #undef PN
 #undef __PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b2d699f28304..20e7d867af7a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1598,7 +1598,7 @@ static void task_numa_compare(struct task_numa_env *env,
         */
        if (cur) {
                /* Skip this swap candidate if cannot move to the source cpu */
-               if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+               if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
                        goto unlock;
 
                /*
@@ -1708,7 +1708,7 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 
        for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
                /* Skip this CPU if the source task cannot migrate */
-               if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
+               if (!cpumask_test_cpu(cpu, env->p->cpus_ptr))
                        continue;
 
                env->dst_cpu = cpu;
@@ -3842,7 +3842,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
        ideal_runtime = sched_slice(cfs_rq, curr);
        delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
        if (delta_exec > ideal_runtime) {
-               resched_curr(rq_of(cfs_rq));
+               resched_curr_lazy(rq_of(cfs_rq));
                /*
                 * The current task ran long enough, ensure it doesn't get
                 * re-elected due to buddy favours.
@@ -3866,7 +3866,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
                return;
 
        if (delta > ideal_runtime)
-               resched_curr(rq_of(cfs_rq));
+               resched_curr_lazy(rq_of(cfs_rq));
 }
 
 static void
@@ -4008,7 +4008,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
         * validating it and just reschedule.
         */
        if (queued) {
-               resched_curr(rq_of(cfs_rq));
+               resched_curr_lazy(rq_of(cfs_rq));
                return;
        }
        /*
@@ -4190,7 +4190,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
         * hierarchy can be throttled
         */
        if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
-               resched_curr(rq_of(cfs_rq));
+               resched_curr_lazy(rq_of(cfs_rq));
 }
 
 static __always_inline
@@ -4686,9 +4686,9 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
        cfs_b->period = ns_to_ktime(default_cfs_period());
 
        INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
-       hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+       hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
        cfs_b->period_timer.function = sched_cfs_period_timer;
-       hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
        cfs_b->slack_timer.function = sched_cfs_slack_timer;
 }
 
@@ -4839,7 +4839,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 
                if (delta < 0) {
                        if (rq->curr == p)
-                               resched_curr(rq);
+                               resched_curr_lazy(rq);
                        return;
                }
                hrtick_start(rq, delta);
@@ -5477,7 +5477,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
                /* Skip over this group if it has no CPUs allowed */
                if (!cpumask_intersects(sched_group_span(group),
-                                       &p->cpus_allowed))
+                                       p->cpus_ptr))
                        continue;
 
                local_group = cpumask_test_cpu(this_cpu,
@@ -5597,7 +5597,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
                return cpumask_first(sched_group_span(group));
 
        /* Traverse only the allowed CPUs */
-       for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
+       for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
                if (idle_cpu(i)) {
                        struct rq *rq = cpu_rq(i);
                        struct cpuidle_state *idle = idle_get_state(rq);
@@ -5700,7 +5700,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
        if (!test_idle_cores(target, false))
                return -1;
 
-       cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
+       cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
        for_each_cpu_wrap(core, cpus, target) {
                bool idle = true;
@@ -5734,7 +5734,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
                return -1;
 
        for_each_cpu(cpu, cpu_smt_mask(target)) {
-               if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+               if (!cpumask_test_cpu(cpu, p->cpus_ptr))
                        continue;
                if (idle_cpu(cpu))
                        return cpu;
@@ -5797,7 +5797,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
        for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
                if (!--nr)
                        return -1;
-               if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+               if (!cpumask_test_cpu(cpu, p->cpus_ptr))
                        continue;
                if (idle_cpu(cpu))
                        break;
@@ -5952,7 +5952,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
        if (sd_flag & SD_BALANCE_WAKE) {
                record_wakee(p);
                want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
-                             && cpumask_test_cpu(cpu, &p->cpus_allowed);
+                             && cpumask_test_cpu(cpu, p->cpus_ptr);
        }
 
        rcu_read_lock();
@@ -6233,7 +6233,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
        return;
 
 preempt:
-       resched_curr(rq);
+       resched_curr_lazy(rq);
        /*
         * Only set the backward buddy when the current task is still
         * on the rq. This can happen when a wakeup gets interleaved
@@ -6701,14 +6701,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
        /*
         * We do not migrate tasks that are:
         * 1) throttled_lb_pair, or
-        * 2) cannot be migrated to this CPU due to cpus_allowed, or
+        * 2) cannot be migrated to this CPU due to cpus_ptr, or
         * 3) running (obviously), or
         * 4) are cache-hot on their current CPU.
         */
        if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
                return 0;
 
-       if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) {
+       if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
                int cpu;
 
                schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
@@ -6728,7 +6728,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 
                /* Prevent to re-select dst_cpu via env's cpus */
                for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
-                       if (cpumask_test_cpu(cpu, &p->cpus_allowed)) {
+                       if (cpumask_test_cpu(cpu, p->cpus_ptr)) {
                                env->flags |= LBF_DST_PINNED;
                                env->new_dst_cpu = cpu;
                                break;
@@ -7297,7 +7297,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 
 /*
  * Group imbalance indicates (and tries to solve) the problem where balancing
- * groups is inadequate due to ->cpus_allowed constraints.
+ * groups is inadequate due to ->cpus_ptr constraints.
  *
  * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a
  * cpumask covering 1 cpu of the first group and 3 cpus of the second group.
@@ -7873,7 +7873,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
        /*
         * If the busiest group is imbalanced the below checks don't
         * work because they assume all things are equal, which typically
-        * isn't true due to cpus_allowed constraints and the like.
+        * isn't true due to cpus_ptr constraints and the like.
         */
        if (busiest->group_type == group_imbalanced)
                goto force_balance;
@@ -8265,7 +8265,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
                         * if the curr task on busiest cpu can't be
                         * moved to this_cpu
                         */
-                       if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+                       if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
                                raw_spin_unlock_irqrestore(&busiest->lock,
                                                            flags);
                                env.flags |= LBF_ALL_PINNED;
@@ -9087,7 +9087,7 @@ static void task_fork_fair(struct task_struct *p)
                 * 'current' within the tree based on its new key value.
                 */
                swap(curr->vruntime, se->vruntime);
-               resched_curr(rq);
+               resched_curr_lazy(rq);
        }
 
        se->vruntime -= cfs_rq->min_vruntime;
@@ -9111,7 +9111,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
         */
        if (rq->curr == p) {
                if (p->prio > oldprio)
-                       resched_curr(rq);
+                       resched_curr_lazy(rq);
        } else
                check_preempt_curr(rq, p, 0);
 }
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 9552fd5854bf..fb069998b518 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -46,11 +46,19 @@ SCHED_FEAT(LB_BIAS, true)
  */
 SCHED_FEAT(NONTASK_CAPACITY, true)
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+SCHED_FEAT(TTWU_QUEUE, false)
+# ifdef CONFIG_PREEMPT_LAZY
+SCHED_FEAT(PREEMPT_LAZY, true)
+# endif
+#else
+
 /*
  * Queue remote wakeups on the target CPU and process them
  * using the scheduler IPI. Reduces rq->lock contention/bounces.
  */
 SCHED_FEAT(TTWU_QUEUE, true)
+#endif
 
 /*
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index cb9a5b8532fa..6c72332dab3f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -47,8 +47,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
 
        raw_spin_lock_init(&rt_b->rt_runtime_lock);
 
-       hrtimer_init(&rt_b->rt_period_timer,
-                       CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
+                    HRTIMER_MODE_REL_HARD);
        rt_b->rt_period_timer.function = sched_rt_period_timer;
 }
 
@@ -1596,7 +1596,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
        if (!task_running(rq, p) &&
-           cpumask_test_cpu(cpu, &p->cpus_allowed))
+           cpumask_test_cpu(cpu, p->cpus_ptr))
                return 1;
        return 0;
 }
@@ -1731,7 +1731,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
                         * Also make sure that it wasn't scheduled on its rq.
                         */
                        if (unlikely(task_rq(task) != rq ||
-                                    !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) ||
+                                    !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
                                     task_running(rq, task) ||
                                     !rt_task(task) ||
                                     !task_on_rq_queued(task))) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b29376169f3f..96481980c8c7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1354,6 +1354,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #define WF_SYNC                0x01            /* waker goes to sleep after wakeup */
 #define WF_FORK                0x02            /* child wakeup after fork */
 #define WF_MIGRATED    0x4             /* internal use, task got migrated */
+#define WF_LOCK_SLEEPER        0x08            /* wakeup spinlock "sleeper" */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1545,6 +1546,15 @@ extern void init_sched_fair_class(void);
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
+#ifdef CONFIG_PREEMPT_LAZY
+extern void resched_curr_lazy(struct rq *rq);
+#else
+static inline void resched_curr_lazy(struct rq *rq)
+{
+       resched_curr(rq);
+}
+#endif
+
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 9ff1555341ed..b14638a05ec9 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/sched/signal.h>
 #include <linux/swait.h>
+#include <linux/suspend.h>
 
 void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
                             struct lock_class_key *key)
@@ -30,6 +31,25 @@ void swake_up_locked(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_locked);
 
+void swake_up_all_locked(struct swait_queue_head *q)
+{
+       struct swait_queue *curr;
+       int wakes = 0;
+
+       while (!list_empty(&q->task_list)) {
+
+               curr = list_first_entry(&q->task_list, typeof(*curr),
+                                       task_list);
+               wake_up_process(curr->task);
+               list_del_init(&curr->task_list);
+               wakes++;
+       }
+       if (pm_in_action)
+               return;
+       WARN(wakes > 2, "complete_all() with %d waiters\n", wakes);
+}
+EXPORT_SYMBOL(swake_up_all_locked);
+
 void swake_up(struct swait_queue_head *q)
 {
        unsigned long flags;
@@ -49,6 +69,7 @@ void swake_up_all(struct swait_queue_head *q)
        struct swait_queue *curr;
        LIST_HEAD(tmp);
 
+       WARN_ON(irqs_disabled());
        raw_spin_lock_irq(&q->lock);
        list_splice_init(&q->task_list, &tmp);
        while (!list_empty(&tmp)) {
diff --git a/kernel/sched/swork.c b/kernel/sched/swork.c
new file mode 100644
index 000000000000..1950f40ca725
--- /dev/null
+++ b/kernel/sched/swork.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de
+ *
+ * Provides a framework for enqueuing callbacks from irq context
+ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context.
+ */
+
+#include <linux/swait.h>
+#include <linux/swork.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#define SWORK_EVENT_PENDING     (1 << 0)
+
+static DEFINE_MUTEX(worker_mutex);
+static struct sworker *glob_worker;
+
+struct sworker {
+       struct list_head events;
+       struct swait_queue_head wq;
+
+       raw_spinlock_t lock;
+
+       struct task_struct *task;
+       int refs;
+};
+
+static bool swork_readable(struct sworker *worker)
+{
+       bool r;
+
+       if (kthread_should_stop())
+               return true;
+
+       raw_spin_lock_irq(&worker->lock);
+       r = !list_empty(&worker->events);
+       raw_spin_unlock_irq(&worker->lock);
+
+       return r;
+}
+
+static int swork_kthread(void *arg)
+{
+       struct sworker *worker = arg;
+
+       for (;;) {
+               swait_event_interruptible(worker->wq,
+                                       swork_readable(worker));
+               if (kthread_should_stop())
+                       break;
+
+               raw_spin_lock_irq(&worker->lock);
+               while (!list_empty(&worker->events)) {
+                       struct swork_event *sev;
+
+                       sev = list_first_entry(&worker->events,
+                                       struct swork_event, item);
+                       list_del(&sev->item);
+                       raw_spin_unlock_irq(&worker->lock);
+
+                       WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING,
+                                                        &sev->flags));
+                       sev->func(sev);
+                       raw_spin_lock_irq(&worker->lock);
+               }
+               raw_spin_unlock_irq(&worker->lock);
+       }
+       return 0;
+}
+
+static struct sworker *swork_create(void)
+{
+       struct sworker *worker;
+
+       worker = kzalloc(sizeof(*worker), GFP_KERNEL);
+       if (!worker)
+               return ERR_PTR(-ENOMEM);
+
+       INIT_LIST_HEAD(&worker->events);
+       raw_spin_lock_init(&worker->lock);
+       init_swait_queue_head(&worker->wq);
+
+       worker->task = kthread_run(swork_kthread, worker, "kswork");
+       if (IS_ERR(worker->task)) {
+               kfree(worker);
+               return ERR_PTR(-ENOMEM);
+       }
+
+       return worker;
+}
+
+static void swork_destroy(struct sworker *worker)
+{
+       kthread_stop(worker->task);
+
+       WARN_ON(!list_empty(&worker->events));
+       kfree(worker);
+}
+
+/**
+ * swork_queue - queue swork
+ *
+ * Returns %false if @work was already on a queue, %true otherwise.
+ *
+ * The work is queued and processed on a random CPU
+ */
+bool swork_queue(struct swork_event *sev)
+{
+       unsigned long flags;
+
+       if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags))
+               return false;
+
+       raw_spin_lock_irqsave(&glob_worker->lock, flags);
+       list_add_tail(&sev->item, &glob_worker->events);
+       raw_spin_unlock_irqrestore(&glob_worker->lock, flags);
+
+       swake_up(&glob_worker->wq);
+       return true;
+}
+EXPORT_SYMBOL_GPL(swork_queue);
+
+/**
+ * swork_get - get an instance of the sworker
+ *
+ * Returns an negative error code if the initialization if the worker did not
+ * work, %0 otherwise.
+ *
+ */
+int swork_get(void)
+{
+       struct sworker *worker;
+
+       mutex_lock(&worker_mutex);
+       if (!glob_worker) {
+               worker = swork_create();
+               if (IS_ERR(worker)) {
+                       mutex_unlock(&worker_mutex);
+                       return -ENOMEM;
+               }
+
+               glob_worker = worker;
+       }
+
+       glob_worker->refs++;
+       mutex_unlock(&worker_mutex);
+
+       return 0;
+}
+EXPORT_SYMBOL_GPL(swork_get);
+
+/**
+ * swork_put - puts an instance of the sworker
+ *
+ * Will destroy the sworker thread. This function must not be called until all
+ * queued events have been completed.
+ */
+void swork_put(void)
+{
+       mutex_lock(&worker_mutex);
+
+       glob_worker->refs--;
+       if (glob_worker->refs > 0)
+               goto out;
+
+       swork_destroy(glob_worker);
+       glob_worker = NULL;
+out:
+       mutex_unlock(&worker_mutex);
+}
+EXPORT_SYMBOL_GPL(swork_put);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 659e075ef70b..bb22e3620a90 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -286,6 +286,7 @@ static int init_rootdomain(struct root_domain *rd)
        rd->rto_cpu = -1;
        raw_spin_lock_init(&rd->rto_lock);
        init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+       rd->rto_push_work.flags |= IRQ_WORK_HARD_IRQ;
 #endif
 
        init_dl_bw(&rd->dl_bw);
diff --git a/kernel/signal.c b/kernel/signal.c
index 4439ba9dc5d9..d8f75a030292 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -19,6 +19,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/rt.h>
 #include <linux/fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
@@ -360,13 +361,30 @@ static bool task_participate_group_stop(struct task_struct *task)
        return false;
 }
 
+static inline struct sigqueue *get_task_cache(struct task_struct *t)
+{
+       struct sigqueue *q = t->sigqueue_cache;
+
+       if (cmpxchg(&t->sigqueue_cache, q, NULL) != q)
+               return NULL;
+       return q;
+}
+
+static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
+{
+       if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL)
+               return 0;
+       return 1;
+}
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
  *   appropriate lock must be held to stop the target task from exiting
  */
 static struct sigqueue *
-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
+__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags,
+                   int override_rlimit, int fromslab)
 {
        struct sigqueue *q = NULL;
        struct user_struct *user;
@@ -383,7 +401,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
        if (override_rlimit ||
            atomic_read(&user->sigpending) <=
                        task_rlimit(t, RLIMIT_SIGPENDING)) {
-               q = kmem_cache_alloc(sigqueue_cachep, flags);
+               if (!fromslab)
+                       q = get_task_cache(t);
+               if (!q)
+                       q = kmem_cache_alloc(sigqueue_cachep, flags);
        } else {
                print_dropped_signal(sig);
        }
@@ -400,6 +421,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
        return q;
 }
 
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags,
+                int override_rlimit)
+{
+       return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0);
+}
+
 static void __sigqueue_free(struct sigqueue *q)
 {
        if (q->flags & SIGQUEUE_PREALLOC)
@@ -409,6 +437,21 @@ static void __sigqueue_free(struct sigqueue *q)
        kmem_cache_free(sigqueue_cachep, q);
 }
 
+static void sigqueue_free_current(struct sigqueue *q)
+{
+       struct user_struct *up;
+
+       if (q->flags & SIGQUEUE_PREALLOC)
+               return;
+
+       up = q->user;
+       if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) {
+               atomic_dec(&up->sigpending);
+               free_uid(up);
+       } else
+                 __sigqueue_free(q);
+}
+
 void flush_sigqueue(struct sigpending *queue)
 {
        struct sigqueue *q;
@@ -421,6 +464,21 @@ void flush_sigqueue(struct sigpending *queue)
        }
 }
 
+/*
+ * Called from __exit_signal. Flush tsk->pending and
+ * tsk->sigqueue_cache
+ */
+void flush_task_sigqueue(struct task_struct *tsk)
+{
+       struct sigqueue *q;
+
+       flush_sigqueue(&tsk->pending);
+
+       q = get_task_cache(tsk);
+       if (q)
+               kmem_cache_free(sigqueue_cachep, q);
+}
+
 /*
  * Flush all pending signals for this kthread.
  */
@@ -542,7 +600,7 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info,
                        (info->si_code == SI_TIMER) &&
                        (info->si_sys_private);
 
-               __sigqueue_free(first);
+               sigqueue_free_current(first);
        } else {
                /*
                 * Ok, it wasn't in the queue.  This must be
@@ -578,6 +636,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
        bool resched_timer = false;
        int signr;
 
+       WARN_ON_ONCE(tsk != current);
+
        /* We only dequeue private signals from ourselves, we don't let
         * signalfd steal them
         */
@@ -1177,8 +1237,8 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
  * We don't want to have recursive SIGSEGV's etc, for example,
  * that is why we also clear SIGNAL_UNKILLABLE.
  */
-int
-force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
+static int
+do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 {
        unsigned long int flags;
        int ret, blocked, ignored;
@@ -1207,6 +1267,39 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
        return ret;
 }
 
+int force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
+{
+/*
+ * On some archs, PREEMPT_RT has to delay sending a signal from a trap
+ * since it can not enable preemption, and the signal code's spin_locks
+ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will
+ * send the signal on exit of the trap.
+ */
+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
+       if (in_atomic()) {
+               if (WARN_ON_ONCE(t != current))
+                       return 0;
+               if (WARN_ON_ONCE(t->forced_info.si_signo))
+                       return 0;
+
+               if (is_si_special(info)) {
+                       WARN_ON_ONCE(info != SEND_SIG_PRIV);
+                       t->forced_info.si_signo = sig;
+                       t->forced_info.si_errno = 0;
+                       t->forced_info.si_code = SI_KERNEL;
+                       t->forced_info.si_pid = 0;
+                       t->forced_info.si_uid = 0;
+               } else {
+                       t->forced_info = *info;
+               }
+
+               set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+               return 0;
+       }
+#endif
+       return do_force_sig_info(sig, info, t);
+}
+
 /*
  * Nuke all other threads in the group.
  */
@@ -1241,12 +1334,12 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
                 * Disable interrupts early to avoid deadlocks.
                 * See rcu_read_unlock() comment header for details.
                 */
-               local_irq_save(*flags);
+               local_irq_save_nort(*flags);
                rcu_read_lock();
                sighand = rcu_dereference(tsk->sighand);
                if (unlikely(sighand == NULL)) {
                        rcu_read_unlock();
-                       local_irq_restore(*flags);
+                       local_irq_restore_nort(*flags);
                        break;
                }
                /*
@@ -1267,7 +1360,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
                }
                spin_unlock(&sighand->siglock);
                rcu_read_unlock();
-               local_irq_restore(*flags);
+               local_irq_restore_nort(*flags);
        }
 
        return sighand;
@@ -1514,7 +1607,8 @@ EXPORT_SYMBOL(kill_pid);
  */
 struct sigqueue *sigqueue_alloc(void)
 {
-       struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
+       /* Preallocated sigqueue objects always from the slabcache ! */
+       struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1);
 
        if (q)
                q->flags |= SIGQUEUE_PREALLOC;
@@ -1888,15 +1982,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
                if (gstop_done && ptrace_reparented(current))
                        do_notify_parent_cldstop(current, false, why);
 
-               /*
-                * Don't want to allow preemption here, because
-                * sys_ptrace() needs this task to be inactive.
-                *
-                * XXX: implement read_unlock_no_resched().
-                */
-               preempt_disable();
                read_unlock(&tasklist_lock);
-               preempt_enable_no_resched();
                freezable_schedule();
        } else {
                /*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index a4c87cf27f9d..583c9ecf04e3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -21,11 +21,14 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/rcupdate.h>
+#include <linux/delay.h>
 #include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/smpboot.h>
 #include <linux/tick.h>
+#include <linux/locallock.h>
 #include <linux/irq.h>
+#include <linux/sched/types.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/irq.h>
@@ -56,12 +59,108 @@ EXPORT_SYMBOL(irq_stat);
 static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
 DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ))
+DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd);
+#endif
 
 const char * const softirq_to_name[NR_SOFTIRQS] = {
        "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL",
        "TASKLET", "SCHED", "HRTIMER", "RCU"
 };
 
+#ifdef CONFIG_NO_HZ_COMMON
+# ifdef CONFIG_PREEMPT_RT_FULL
+
+struct softirq_runner {
+       struct task_struct *runner[NR_SOFTIRQS];
+};
+
+static DEFINE_PER_CPU(struct softirq_runner, softirq_runners);
+
+static inline void softirq_set_runner(unsigned int sirq)
+{
+       struct softirq_runner *sr = this_cpu_ptr(&softirq_runners);
+
+       sr->runner[sirq] = current;
+}
+
+static inline void softirq_clr_runner(unsigned int sirq)
+{
+       struct softirq_runner *sr = this_cpu_ptr(&softirq_runners);
+
+       sr->runner[sirq] = NULL;
+}
+
+/*
+ * On preempt-rt a softirq running context might be blocked on a
+ * lock. There might be no other runnable task on this CPU because the
+ * lock owner runs on some other CPU. So we have to go into idle with
+ * the pending bit set. Therefor we need to check this otherwise we
+ * warn about false positives which confuses users and defeats the
+ * whole purpose of this test.
+ *
+ * This code is called with interrupts disabled.
+ */
+void softirq_check_pending_idle(void)
+{
+       static int rate_limit;
+       struct softirq_runner *sr = this_cpu_ptr(&softirq_runners);
+       u32 warnpending;
+       int i;
+
+       if (rate_limit >= 10)
+               return;
+
+       warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK;
+       for (i = 0; i < NR_SOFTIRQS; i++) {
+               struct task_struct *tsk = sr->runner[i];
+
+               /*
+                * The wakeup code in rtmutex.c wakes up the task
+                * _before_ it sets pi_blocked_on to NULL under
+                * tsk->pi_lock. So we need to check for both: state
+                * and pi_blocked_on.
+                */
+               if (tsk) {
+                       raw_spin_lock(&tsk->pi_lock);
+                       if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) {
+                               /* Clear all bits pending in that task */
+                               warnpending &= ~(tsk->softirqs_raised);
+                               warnpending &= ~(1 << i);
+                       }
+                       raw_spin_unlock(&tsk->pi_lock);
+               }
+       }
+
+       if (warnpending) {
+               printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+                      warnpending);
+               rate_limit++;
+       }
+}
+# else
+/*
+ * On !PREEMPT_RT we just printk rate limited:
+ */
+void softirq_check_pending_idle(void)
+{
+       static int rate_limit;
+
+       if (rate_limit < 10 && !in_softirq() &&
+                       (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
+               printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+                      local_softirq_pending());
+               rate_limit++;
+       }
+}
+# endif
+
+#else /* !CONFIG_NO_HZ_COMMON */
+static inline void softirq_set_runner(unsigned int sirq) { }
+static inline void softirq_clr_runner(unsigned int sirq) { }
+#endif
+
 /*
  * we cannot loop indefinitely here to avoid userspace starvation,
  * but we also don't want to introduce a worst case 1/HZ latency
@@ -77,6 +176,38 @@ static void wakeup_softirqd(void)
                wake_up_process(tsk);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void wakeup_timer_softirqd(void)
+{
+       /* Interrupts are disabled: no need to stop preemption */
+       struct task_struct *tsk = __this_cpu_read(ktimer_softirqd);
+
+       if (tsk && tsk->state != TASK_RUNNING)
+               wake_up_process(tsk);
+}
+#endif
+
+static void handle_softirq(unsigned int vec_nr)
+{
+       struct softirq_action *h = softirq_vec + vec_nr;
+       int prev_count;
+
+       prev_count = preempt_count();
+
+       kstat_incr_softirqs_this_cpu(vec_nr);
+
+       trace_softirq_entry(vec_nr);
+       h->action(h);
+       trace_softirq_exit(vec_nr);
+       if (unlikely(prev_count != preempt_count())) {
+               pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
+                      vec_nr, softirq_to_name[vec_nr], h->action,
+                      prev_count, preempt_count());
+               preempt_count_set(prev_count);
+       }
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * If ksoftirqd is scheduled, we do not want to process pending softirqs
  * right now. Let ksoftirqd handle this at its own rate, to get fairness,
@@ -92,6 +223,47 @@ static bool ksoftirqd_running(unsigned long pending)
        return tsk && (tsk->state == TASK_RUNNING);
 }
 
+static inline int ksoftirqd_softirq_pending(void)
+{
+       return local_softirq_pending();
+}
+
+static void handle_pending_softirqs(u32 pending)
+{
+       struct softirq_action *h = softirq_vec;
+       int softirq_bit;
+
+       local_irq_enable();
+
+       h = softirq_vec;
+
+       while ((softirq_bit = ffs(pending))) {
+               unsigned int vec_nr;
+
+               h += softirq_bit - 1;
+               vec_nr = h - softirq_vec;
+               handle_softirq(vec_nr);
+
+               h++;
+               pending >>= softirq_bit;
+       }
+
+       rcu_bh_qs();
+       local_irq_disable();
+}
+
+static void run_ksoftirqd(unsigned int cpu)
+{
+       local_irq_disable();
+       if (ksoftirqd_softirq_pending()) {
+               __do_softirq();
+               local_irq_enable();
+               cond_resched_rcu_qs();
+               return;
+       }
+       local_irq_enable();
+}
+
 /*
  * preempt_count and SOFTIRQ_OFFSET usage:
  * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
@@ -247,10 +419,8 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
        unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
        unsigned long old_flags = current->flags;
        int max_restart = MAX_SOFTIRQ_RESTART;
-       struct softirq_action *h;
        bool in_hardirq;
        __u32 pending;
-       int softirq_bit;
 
        /*
         * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -269,36 +439,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
        /* Reset the pending bitmask before enabling irqs */
        set_softirq_pending(0);
 
-       local_irq_enable();
-
-       h = softirq_vec;
-
-       while ((softirq_bit = ffs(pending))) {
-               unsigned int vec_nr;
-               int prev_count;
-
-               h += softirq_bit - 1;
-
-               vec_nr = h - softirq_vec;
-               prev_count = preempt_count();
-
-               kstat_incr_softirqs_this_cpu(vec_nr);
-
-               trace_softirq_entry(vec_nr);
-               h->action(h);
-               trace_softirq_exit(vec_nr);
-               if (unlikely(prev_count != preempt_count())) {
-                       pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
-                              vec_nr, softirq_to_name[vec_nr], h->action,
-                              prev_count, preempt_count());
-                       preempt_count_set(prev_count);
-               }
-               h++;
-               pending >>= softirq_bit;
-       }
-
-       rcu_bh_qs();
-       local_irq_disable();
+       handle_pending_softirqs(pending);
 
        pending = local_softirq_pending();
        if (pending) {
@@ -334,6 +475,309 @@ asmlinkage __visible void do_softirq(void)
        local_irq_restore(flags);
 }
 
+/*
+ * This function must run with irqs disabled!
+ */
+void raise_softirq_irqoff(unsigned int nr)
+{
+       __raise_softirq_irqoff(nr);
+
+       /*
+        * If we're in an interrupt or softirq, we're done
+        * (this also catches softirq-disabled code). We will
+        * actually run the softirq once we return from
+        * the irq or softirq.
+        *
+        * Otherwise we wake up ksoftirqd to make sure we
+        * schedule the softirq soon.
+        */
+       if (!in_interrupt())
+               wakeup_softirqd();
+}
+
+void __raise_softirq_irqoff(unsigned int nr)
+{
+       trace_softirq_raise(nr);
+       or_softirq_pending(1UL << nr);
+}
+
+static inline void local_bh_disable_nort(void) { local_bh_disable(); }
+static inline void _local_bh_enable_nort(void) { _local_bh_enable(); }
+static void ksoftirqd_set_sched_params(unsigned int cpu) { }
+
+#else /* !PREEMPT_RT_FULL */
+
+/*
+ * On RT we serialize softirq execution with a cpu local lock per softirq
+ */
+static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks);
+
+void __init softirq_early_init(void)
+{
+       int i;
+
+       for (i = 0; i < NR_SOFTIRQS; i++)
+               local_irq_lock_init(local_softirq_locks[i]);
+}
+
+static void lock_softirq(int which)
+{
+       local_lock(local_softirq_locks[which]);
+}
+
+static void unlock_softirq(int which)
+{
+       local_unlock(local_softirq_locks[which]);
+}
+
+static void do_single_softirq(int which)
+{
+       unsigned long old_flags = current->flags;
+
+       current->flags &= ~PF_MEMALLOC;
+       vtime_account_irq_enter(current);
+       current->flags |= PF_IN_SOFTIRQ;
+       lockdep_softirq_enter();
+       local_irq_enable();
+       handle_softirq(which);
+       local_irq_disable();
+       lockdep_softirq_exit();
+       current->flags &= ~PF_IN_SOFTIRQ;
+       vtime_account_irq_enter(current);
+       current_restore_flags(old_flags, PF_MEMALLOC);
+}
+
+/*
+ * Called with interrupts disabled. Process softirqs which were raised
+ * in current context (or on behalf of ksoftirqd).
+ */
+static void do_current_softirqs(void)
+{
+       while (current->softirqs_raised) {
+               int i = __ffs(current->softirqs_raised);
+               unsigned int pending, mask = (1U << i);
+
+               current->softirqs_raised &= ~mask;
+               local_irq_enable();
+
+               /*
+                * If the lock is contended, we boost the owner to
+                * process the softirq or leave the critical section
+                * now.
+                */
+               lock_softirq(i);
+               local_irq_disable();
+               softirq_set_runner(i);
+               /*
+                * Check with the local_softirq_pending() bits,
+                * whether we need to process this still or if someone
+                * else took care of it.
+                */
+               pending = local_softirq_pending();
+               if (pending & mask) {
+                       set_softirq_pending(pending & ~mask);
+                       do_single_softirq(i);
+               }
+               softirq_clr_runner(i);
+               WARN_ON(current->softirq_nestcnt != 1);
+               local_irq_enable();
+               unlock_softirq(i);
+               local_irq_disable();
+       }
+}
+
+void __local_bh_disable(void)
+{
+       if (++current->softirq_nestcnt == 1)
+               migrate_disable();
+}
+EXPORT_SYMBOL(__local_bh_disable);
+
+void __local_bh_enable(void)
+{
+       if (WARN_ON(current->softirq_nestcnt == 0))
+               return;
+
+       local_irq_disable();
+       if (current->softirq_nestcnt == 1 && current->softirqs_raised)
+               do_current_softirqs();
+       local_irq_enable();
+
+       if (--current->softirq_nestcnt == 0)
+               migrate_enable();
+}
+EXPORT_SYMBOL(__local_bh_enable);
+
+void _local_bh_enable(void)
+{
+       if (WARN_ON(current->softirq_nestcnt == 0))
+               return;
+       if (--current->softirq_nestcnt == 0)
+               migrate_enable();
+}
+EXPORT_SYMBOL(_local_bh_enable);
+
+int in_serving_softirq(void)
+{
+       return current->flags & PF_IN_SOFTIRQ;
+}
+EXPORT_SYMBOL(in_serving_softirq);
+
+/* Called with preemption disabled */
+static void run_ksoftirqd(unsigned int cpu)
+{
+       local_irq_disable();
+       current->softirq_nestcnt++;
+
+       do_current_softirqs();
+       current->softirq_nestcnt--;
+       local_irq_enable();
+       cond_resched_rcu_qs();
+}
+
+/*
+ * Called from netif_rx_ni(). Preemption enabled, but migration
+ * disabled. So the cpu can't go away under us.
+ */
+void thread_do_softirq(void)
+{
+       if (!in_serving_softirq() && current->softirqs_raised) {
+               current->softirq_nestcnt++;
+               do_current_softirqs();
+               current->softirq_nestcnt--;
+       }
+}
+
+static void do_raise_softirq_irqoff(unsigned int nr)
+{
+       unsigned int mask;
+
+       mask = 1UL << nr;
+
+       trace_softirq_raise(nr);
+       or_softirq_pending(mask);
+
+       /*
+        * If we are not in a hard interrupt and inside a bh disabled
+        * region, we simply raise the flag on current. local_bh_enable()
+        * will make sure that the softirq is executed. Otherwise we
+        * delegate it to ksoftirqd.
+        */
+       if (!in_irq() && current->softirq_nestcnt)
+               current->softirqs_raised |= mask;
+       else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd))
+               return;
+
+       if (mask & TIMER_SOFTIRQS)
+               __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask;
+       else
+               __this_cpu_read(ksoftirqd)->softirqs_raised |= mask;
+}
+
+static void wakeup_proper_softirq(unsigned int nr)
+{
+       if ((1UL << nr) & TIMER_SOFTIRQS)
+               wakeup_timer_softirqd();
+       else
+               wakeup_softirqd();
+}
+
+void __raise_softirq_irqoff(unsigned int nr)
+{
+       do_raise_softirq_irqoff(nr);
+       if (!in_irq() && !current->softirq_nestcnt)
+               wakeup_proper_softirq(nr);
+}
+
+/*
+ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd
+ */
+void __raise_softirq_irqoff_ksoft(unsigned int nr)
+{
+       unsigned int mask;
+
+       if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) ||
+                        !__this_cpu_read(ktimer_softirqd)))
+               return;
+       mask = 1UL << nr;
+
+       trace_softirq_raise(nr);
+       or_softirq_pending(mask);
+       if (mask & TIMER_SOFTIRQS)
+               __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask;
+       else
+               __this_cpu_read(ksoftirqd)->softirqs_raised |= mask;
+       wakeup_proper_softirq(nr);
+}
+
+/*
+ * This function must run with irqs disabled!
+ */
+void raise_softirq_irqoff(unsigned int nr)
+{
+       do_raise_softirq_irqoff(nr);
+
+       /*
+        * If we're in an hard interrupt we let irq return code deal
+        * with the wakeup of ksoftirqd.
+        */
+       if (in_irq())
+               return;
+       /*
+        * If we are in thread context but outside of a bh disabled
+        * region, we need to wake ksoftirqd as well.
+        *
+        * CHECKME: Some of the places which do that could be wrapped
+        * into local_bh_disable/enable pairs. Though it's unclear
+        * whether this is worth the effort. To find those places just
+        * raise a WARN() if the condition is met.
+        */
+       if (!current->softirq_nestcnt)
+               wakeup_proper_softirq(nr);
+}
+
+static inline int ksoftirqd_softirq_pending(void)
+{
+       return current->softirqs_raised;
+}
+
+static inline void local_bh_disable_nort(void) { }
+static inline void _local_bh_enable_nort(void) { }
+
+static inline void ksoftirqd_set_sched_params(unsigned int cpu)
+{
+       /* Take over all but timer pending softirqs when starting */
+       local_irq_disable();
+       current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS;
+       local_irq_enable();
+}
+
+static inline void ktimer_softirqd_set_sched_params(unsigned int cpu)
+{
+       struct sched_param param = { .sched_priority = 1 };
+
+       sched_setscheduler(current, SCHED_FIFO, &param);
+
+       /* Take over timer pending softirqs when starting */
+       local_irq_disable();
+       current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS;
+       local_irq_enable();
+}
+
+static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu,
+                                                   bool online)
+{
+       struct sched_param param = { .sched_priority = 0 };
+
+       sched_setscheduler(current, SCHED_NORMAL, &param);
+}
+
+static int ktimer_softirqd_should_run(unsigned int cpu)
+{
+       return current->softirqs_raised;
+}
+
+#endif /* PREEMPT_RT_FULL */
 /*
  * Enter an interrupt context.
  */
@@ -345,9 +789,9 @@ void irq_enter(void)
                 * Prevent raise_softirq from needlessly waking up ksoftirqd
                 * here, as softirq will be serviced on return from interrupt.
                 */
-               local_bh_disable();
+               local_bh_disable_nort();
                tick_irq_enter();
-               _local_bh_enable();
+               _local_bh_enable_nort();
        }
 
        __irq_enter();
@@ -355,6 +799,7 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
        if (ksoftirqd_running(local_softirq_pending()))
                return;
 
@@ -377,6 +822,18 @@ static inline void invoke_softirq(void)
        } else {
                wakeup_softirqd();
        }
+#else /* PREEMPT_RT_FULL */
+       unsigned long flags;
+
+       local_irq_save(flags);
+       if (__this_cpu_read(ksoftirqd) &&
+                       __this_cpu_read(ksoftirqd)->softirqs_raised)
+               wakeup_softirqd();
+       if (__this_cpu_read(ktimer_softirqd) &&
+                       __this_cpu_read(ktimer_softirqd)->softirqs_raised)
+               wakeup_timer_softirqd();
+       local_irq_restore(flags);
+#endif
 }
 
 static inline void tick_irq_exit(void)
@@ -385,7 +842,8 @@ static inline void tick_irq_exit(void)
        int cpu = smp_processor_id();
 
        /* Make sure that timer wheel updates are propagated */
-       if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
+       if ((idle_cpu(cpu) || tick_nohz_full_cpu(cpu)) &&
+           !need_resched() && !local_softirq_pending()) {
                if (!in_irq())
                        tick_nohz_irq_exit();
        }
@@ -413,26 +871,6 @@ void irq_exit(void)
        trace_hardirq_exit(); /* must be last! */
 }
 
-/*
- * This function must run with irqs disabled!
- */
-inline void raise_softirq_irqoff(unsigned int nr)
-{
-       __raise_softirq_irqoff(nr);
-
-       /*
-        * If we're in an interrupt or softirq, we're done
-        * (this also catches softirq-disabled code). We will
-        * actually run the softirq once we return from
-        * the irq or softirq.
-        *
-        * Otherwise we wake up ksoftirqd to make sure we
-        * schedule the softirq soon.
-        */
-       if (!in_interrupt())
-               wakeup_softirqd();
-}
-
 void raise_softirq(unsigned int nr)
 {
        unsigned long flags;
@@ -442,12 +880,6 @@ void raise_softirq(unsigned int nr)
        local_irq_restore(flags);
 }
 
-void __raise_softirq_irqoff(unsigned int nr)
-{
-       trace_softirq_raise(nr);
-       or_softirq_pending(1UL << nr);
-}
-
 void open_softirq(int nr, void (*action)(struct softirq_action *))
 {
        softirq_vec[nr].action = action;
@@ -464,15 +896,45 @@ struct tasklet_head {
 static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
 static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
 
+static void inline
+__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr)
+{
+       if (tasklet_trylock(t)) {
+again:
+               /* We may have been preempted before tasklet_trylock
+                * and __tasklet_action may have already run.
+                * So double check the sched bit while the takslet
+                * is locked before adding it to the list.
+                */
+               if (test_bit(TASKLET_STATE_SCHED, &t->state)) {
+                       t->next = NULL;
+                       *head->tail = t;
+                       head->tail = &(t->next);
+                       raise_softirq_irqoff(nr);
+                       tasklet_unlock(t);
+               } else {
+                       /* This is subtle. If we hit the corner case above
+                        * It is possible that we get preempted right here,
+                        * and another task has successfully called
+                        * tasklet_schedule(), then this function, and
+                        * failed on the trylock. Thus we must be sure
+                        * before releasing the tasklet lock, that the
+                        * SCHED_BIT is clear. Otherwise the tasklet
+                        * may get its SCHED_BIT set, but not added to the
+                        * list
+                        */
+                       if (!tasklet_tryunlock(t))
+                               goto again;
+               }
+       }
+}
+
 void __tasklet_schedule(struct tasklet_struct *t)
 {
        unsigned long flags;
 
        local_irq_save(flags);
-       t->next = NULL;
-       *__this_cpu_read(tasklet_vec.tail) = t;
-       __this_cpu_write(tasklet_vec.tail, &(t->next));
-       raise_softirq_irqoff(TASKLET_SOFTIRQ);
+       __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
        local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__tasklet_schedule);
@@ -482,50 +944,108 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
        unsigned long flags;
 
        local_irq_save(flags);
-       t->next = NULL;
-       *__this_cpu_read(tasklet_hi_vec.tail) = t;
-       __this_cpu_write(tasklet_hi_vec.tail,  &(t->next));
-       raise_softirq_irqoff(HI_SOFTIRQ);
+       __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
        local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__tasklet_hi_schedule);
 
-static __latent_entropy void tasklet_action(struct softirq_action *a)
+void tasklet_enable(struct tasklet_struct *t)
 {
-       struct tasklet_struct *list;
+       if (!atomic_dec_and_test(&t->count))
+               return;
+       if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state))
+               tasklet_schedule(t);
+}
+EXPORT_SYMBOL(tasklet_enable);
 
-       local_irq_disable();
-       list = __this_cpu_read(tasklet_vec.head);
-       __this_cpu_write(tasklet_vec.head, NULL);
-       __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
-       local_irq_enable();
+static void __tasklet_action(struct softirq_action *a,
+                            struct tasklet_struct *list)
+{
+       int loops = 1000000;
 
        while (list) {
                struct tasklet_struct *t = list;
 
                list = list->next;
 
-               if (tasklet_trylock(t)) {
-                       if (!atomic_read(&t->count)) {
-                               if (!test_and_clear_bit(TASKLET_STATE_SCHED,
-                                                       &t->state))
-                                       BUG();
-                               t->func(t->data);
-                               tasklet_unlock(t);
-                               continue;
-                       }
-                       tasklet_unlock(t);
+               /*
+                * Should always succeed - after a tasklist got on the
+                * list (after getting the SCHED bit set from 0 to 1),
+                * nothing but the tasklet softirq it got queued to can
+                * lock it:
+                */
+               if (!tasklet_trylock(t)) {
+                       WARN_ON(1);
+                       continue;
                }
 
-               local_irq_disable();
                t->next = NULL;
-               *__this_cpu_read(tasklet_vec.tail) = t;
-               __this_cpu_write(tasklet_vec.tail, &(t->next));
-               __raise_softirq_irqoff(TASKLET_SOFTIRQ);
-               local_irq_enable();
+
+               /*
+                * If we cannot handle the tasklet because it's disabled,
+                * mark it as pending. tasklet_enable() will later
+                * re-schedule the tasklet.
+                */
+               if (unlikely(atomic_read(&t->count))) {
+out_disabled:
+                       /* implicit unlock: */
+                       wmb();
+                       t->state = TASKLET_STATEF_PENDING;
+                       continue;
+               }
+
+               /*
+                * After this point on the tasklet might be rescheduled
+                * on another CPU, but it can only be added to another
+                * CPU's tasklet list if we unlock the tasklet (which we
+                * dont do yet).
+                */
+               if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+                       WARN_ON(1);
+
+again:
+               t->func(t->data);
+
+               /*
+                * Try to unlock the tasklet. We must use cmpxchg, because
+                * another CPU might have scheduled or disabled the tasklet.
+                * We only allow the STATE_RUN -> 0 transition here.
+                */
+               while (!tasklet_tryunlock(t)) {
+                       /*
+                        * If it got disabled meanwhile, bail out:
+                        */
+                       if (atomic_read(&t->count))
+                               goto out_disabled;
+                       /*
+                        * If it got scheduled meanwhile, re-execute
+                        * the tasklet function:
+                        */
+                       if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+                               goto again;
+                       if (!--loops) {
+                               printk("hm, tasklet state: %08lx\n", t->state);
+                               WARN_ON(1);
+                               tasklet_unlock(t);
+                               break;
+                       }
+               }
        }
 }
 
+static __latent_entropy void tasklet_action(struct softirq_action *a)
+{
+       struct tasklet_struct *list;
+
+       local_irq_disable();
+       list = __this_cpu_read(tasklet_vec.head);
+       __this_cpu_write(tasklet_vec.head, NULL);
+       __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
+       local_irq_enable();
+
+       __tasklet_action(a, list);
+}
+
 static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
 {
        struct tasklet_struct *list;
@@ -536,30 +1056,7 @@ static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
        __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head));
        local_irq_enable();
 
-       while (list) {
-               struct tasklet_struct *t = list;
-
-               list = list->next;
-
-               if (tasklet_trylock(t)) {
-                       if (!atomic_read(&t->count)) {
-                               if (!test_and_clear_bit(TASKLET_STATE_SCHED,
-                                                       &t->state))
-                                       BUG();
-                               t->func(t->data);
-                               tasklet_unlock(t);
-                               continue;
-                       }
-                       tasklet_unlock(t);
-               }
-
-               local_irq_disable();
-               t->next = NULL;
-               *__this_cpu_read(tasklet_hi_vec.tail) = t;
-               __this_cpu_write(tasklet_hi_vec.tail, &(t->next));
-               __raise_softirq_irqoff(HI_SOFTIRQ);
-               local_irq_enable();
-       }
+       __tasklet_action(a, list);
 }
 
 void tasklet_init(struct tasklet_struct *t,
@@ -580,7 +1077,7 @@ void tasklet_kill(struct tasklet_struct *t)
 
        while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
                do {
-                       yield();
+                       msleep(1);
                } while (test_bit(TASKLET_STATE_SCHED, &t->state));
        }
        tasklet_unlock_wait(t);
@@ -588,57 +1085,6 @@ void tasklet_kill(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(tasklet_kill);
 
-/*
- * tasklet_hrtimer
- */
-
-/*
- * The trampoline is called when the hrtimer expires. It schedules a tasklet
- * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
- * hrtimer callback, but from softirq context.
- */
-static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
-{
-       struct tasklet_hrtimer *ttimer =
-               container_of(timer, struct tasklet_hrtimer, timer);
-
-       tasklet_hi_schedule(&ttimer->tasklet);
-       return HRTIMER_NORESTART;
-}
-
-/*
- * Helper function which calls the hrtimer callback from
- * tasklet/softirq context
- */
-static void __tasklet_hrtimer_trampoline(unsigned long data)
-{
-       struct tasklet_hrtimer *ttimer = (void *)data;
-       enum hrtimer_restart restart;
-
-       restart = ttimer->function(&ttimer->timer);
-       if (restart != HRTIMER_NORESTART)
-               hrtimer_restart(&ttimer->timer);
-}
-
-/**
- * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
- * @ttimer:     tasklet_hrtimer which is initialized
- * @function:   hrtimer callback function which gets called from softirq context
- * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
- * @mode:       hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
- */
-void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-                         enum hrtimer_restart (*function)(struct hrtimer *),
-                         clockid_t which_clock, enum hrtimer_mode mode)
-{
-       hrtimer_init(&ttimer->timer, which_clock, mode);
-       ttimer->timer.function = __hrtimer_tasklet_trampoline;
-       tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
-                    (unsigned long)ttimer);
-       ttimer->function = function;
-}
-EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
-
 void __init softirq_init(void)
 {
        int cpu;
@@ -654,25 +1100,26 @@ void __init softirq_init(void)
        open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
 
-static int ksoftirqd_should_run(unsigned int cpu)
-{
-       return local_softirq_pending();
-}
-
-static void run_ksoftirqd(unsigned int cpu)
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
+void tasklet_unlock_wait(struct tasklet_struct *t)
 {
-       local_irq_disable();
-       if (local_softirq_pending()) {
+       while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
                /*
-                * We can safely run softirq on inline stack, as we are not deep
-                * in the task stack here.
+                * Hack for now to avoid this busy-loop:
                 */
-               __do_softirq();
-               local_irq_enable();
-               cond_resched_rcu_qs();
-               return;
+#ifdef CONFIG_PREEMPT_RT_FULL
+               msleep(1);
+#else
+               barrier();
+#endif
        }
-       local_irq_enable();
+}
+EXPORT_SYMBOL(tasklet_unlock_wait);
+#endif
+
+static int ksoftirqd_should_run(unsigned int cpu)
+{
+       return ksoftirqd_softirq_pending();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -739,17 +1186,31 @@ static int takeover_tasklets(unsigned int cpu)
 
 static struct smp_hotplug_thread softirq_threads = {
        .store                  = &ksoftirqd,
+       .setup                  = ksoftirqd_set_sched_params,
        .thread_should_run      = ksoftirqd_should_run,
        .thread_fn              = run_ksoftirqd,
        .thread_comm            = "ksoftirqd/%u",
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static struct smp_hotplug_thread softirq_timer_threads = {
+       .store                  = &ktimer_softirqd,
+       .setup                  = ktimer_softirqd_set_sched_params,
+       .cleanup                = ktimer_softirqd_clr_sched_params,
+       .thread_should_run      = ktimer_softirqd_should_run,
+       .thread_fn              = run_ksoftirqd,
+       .thread_comm            = "ktimersoftd/%u",
+};
+#endif
+
 static __init int spawn_ksoftirqd(void)
 {
        cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL,
                                  takeover_tasklets);
        BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
-
+#ifdef CONFIG_PREEMPT_RT_FULL
+       BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads));
+#endif
        return 0;
 }
 early_initcall(spawn_ksoftirqd);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 067cb83f37ea..56f2f2e01229 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -503,6 +503,8 @@ static void cpu_stopper_thread(unsigned int cpu)
                struct cpu_stop_done *done = work->done;
                int ret;
 
+               /* XXX */
+
                /* cpu stop callbacks must not sleep, make in_atomic() == T */
                preempt_count_inc();
                ret = fn(arg);
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index fa5de5e8de61..6020ee66e517 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -436,7 +436,7 @@ int alarm_cancel(struct alarm *alarm)
                int ret = alarm_try_to_cancel(alarm);
                if (ret >= 0)
                        return ret;
-               cpu_relax();
+               hrtimer_wait_for_timer(&alarm->timer);
        }
 }
 EXPORT_SYMBOL_GPL(alarm_cancel);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index d00e85ac10d6..b59e009087a9 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -59,6 +59,15 @@
 
 #include "tick-internal.h"
 
+/*
+ * Masks for selecting the soft and hard context timers from
+ * cpu_base->active
+ */
+#define MASK_SHIFT             (HRTIMER_BASE_MONOTONIC_SOFT)
+#define HRTIMER_ACTIVE_HARD    ((1U << MASK_SHIFT) - 1)
+#define HRTIMER_ACTIVE_SOFT    (HRTIMER_ACTIVE_HARD << MASK_SHIFT)
+#define HRTIMER_ACTIVE_ALL     (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
+
 /*
  * The timer bases:
  *
@@ -70,7 +79,6 @@
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
        .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
-       .seq = SEQCNT_ZERO(hrtimer_bases.seq),
        .clock_base =
        {
                {
@@ -93,6 +101,26 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
                        .clockid = CLOCK_TAI,
                        .get_time = &ktime_get_clocktai,
                },
+               {
+                       .index = HRTIMER_BASE_MONOTONIC_SOFT,
+                       .clockid = CLOCK_MONOTONIC,
+                       .get_time = &ktime_get,
+               },
+               {
+                       .index = HRTIMER_BASE_REALTIME_SOFT,
+                       .clockid = CLOCK_REALTIME,
+                       .get_time = &ktime_get_real,
+               },
+               {
+                       .index = HRTIMER_BASE_BOOTTIME_SOFT,
+                       .clockid = CLOCK_BOOTTIME,
+                       .get_time = &ktime_get_boottime,
+               },
+               {
+                       .index = HRTIMER_BASE_TAI_SOFT,
+                       .clockid = CLOCK_TAI,
+                       .get_time = &ktime_get_clocktai,
+               },
        }
 };
 
@@ -118,7 +146,6 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
  * timer->base->cpu_base
  */
 static struct hrtimer_cpu_base migration_cpu_base = {
-       .seq = SEQCNT_ZERO(migration_cpu_base),
        .clock_base = { { .cpu_base = &migration_cpu_base, }, },
 };
 
@@ -156,45 +183,33 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 }
 
 /*
- * With HIGHRES=y we do not migrate the timer when it is expiring
- * before the next event on the target cpu because we cannot reprogram
- * the target cpu hardware and we would cause it to fire late.
+ * We do not migrate the timer when it is expiring before the next
+ * event on the target cpu. When high resolution is enabled, we cannot
+ * reprogram the target cpu hardware and we would cause it to fire
+ * late. To keep it simple, we handle the high resolution enabled and
+ * disabled case similar.
  *
  * Called with cpu_base->lock of target cpu held.
  */
 static int
 hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 {
-#ifdef CONFIG_HIGH_RES_TIMERS
        ktime_t expires;
 
-       if (!new_base->cpu_base->hres_active)
-               return 0;
-
        expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
-       return expires <= new_base->cpu_base->expires_next;
-#else
-       return 0;
-#endif
+       return expires < new_base->cpu_base->expires_next;
 }
 
-#ifdef CONFIG_NO_HZ_COMMON
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
-                                        int pinned)
-{
-       if (pinned || !base->migration_enabled)
-               return base;
-       return &per_cpu(hrtimer_bases, get_nohz_timer_target());
-}
-#else
 static inline
 struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
                                         int pinned)
 {
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+       if (static_branch_unlikely(&timers_migration_enabled) && !pinned)
+               return &per_cpu(hrtimer_bases, get_nohz_timer_target());
+#endif
        return base;
 }
-#endif
 
 /*
  * We switch the timer base to a power-optimized selected CPU target,
@@ -396,7 +411,8 @@ static inline void debug_hrtimer_init(struct hrtimer *timer)
        debug_object_init(timer, &hrtimer_debug_descr);
 }
 
-static inline void debug_hrtimer_activate(struct hrtimer *timer)
+static inline void debug_hrtimer_activate(struct hrtimer *timer,
+                                         enum hrtimer_mode mode)
 {
        debug_object_activate(timer, &hrtimer_debug_descr);
 }
@@ -429,8 +445,10 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer)
 EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
 
 #else
+
 static inline void debug_hrtimer_init(struct hrtimer *timer) { }
-static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
+static inline void debug_hrtimer_activate(struct hrtimer *timer,
+                                         enum hrtimer_mode mode) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
@@ -442,10 +460,11 @@ debug_init(struct hrtimer *timer, clockid_t clockid,
        trace_hrtimer_init(timer, clockid, mode);
 }
 
-static inline void debug_activate(struct hrtimer *timer)
+static inline void debug_activate(struct hrtimer *timer,
+                                 enum hrtimer_mode mode)
 {
-       debug_hrtimer_activate(timer);
-       trace_hrtimer_start(timer);
+       debug_hrtimer_activate(timer, mode);
+       trace_hrtimer_start(timer, mode);
 }
 
 static inline void debug_deactivate(struct hrtimer *timer)
@@ -454,35 +473,43 @@ static inline void debug_deactivate(struct hrtimer *timer)
        trace_hrtimer_cancel(timer);
 }
 
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
-static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
-                                            struct hrtimer *timer)
+static struct hrtimer_clock_base *
+__next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active)
 {
-#ifdef CONFIG_HIGH_RES_TIMERS
-       cpu_base->next_timer = timer;
-#endif
+       unsigned int idx;
+
+       if (!*active)
+               return NULL;
+
+       idx = __ffs(*active);
+       *active &= ~(1U << idx);
+
+       return &cpu_base->clock_base[idx];
 }
 
-static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
+#define for_each_active_base(base, cpu_base, active)   \
+       while ((base = __next_base((cpu_base), &(active))))
+
+static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
+                                        unsigned int active,
+                                        ktime_t expires_next)
 {
-       struct hrtimer_clock_base *base = cpu_base->clock_base;
-       unsigned int active = cpu_base->active_bases;
-       ktime_t expires, expires_next = KTIME_MAX;
+       struct hrtimer_clock_base *base;
+       ktime_t expires;
 
-       hrtimer_update_next_timer(cpu_base, NULL);
-       for (; active; base++, active >>= 1) {
+       for_each_active_base(base, cpu_base, active) {
                struct timerqueue_node *next;
                struct hrtimer *timer;
 
-               if (!(active & 0x01))
-                       continue;
-
                next = timerqueue_getnext(&base->active);
                timer = container_of(next, struct hrtimer, node);
                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                if (expires < expires_next) {
                        expires_next = expires;
-                       hrtimer_update_next_timer(cpu_base, timer);
+                       if (timer->is_soft)
+                               cpu_base->softirq_next_timer = timer;
+                       else
+                               cpu_base->next_timer = timer;
                }
        }
        /*
@@ -494,7 +521,47 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
                expires_next = 0;
        return expires_next;
 }
-#endif
+
+/*
+ * Recomputes cpu_base::*next_timer and returns the earliest expires_next but
+ * does not set cpu_base::*expires_next, that is done by hrtimer_reprogram.
+ *
+ * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases,
+ * those timers will get run whenever the softirq gets handled, at the end of
+ * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases.
+ *
+ * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases.
+ * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual
+ * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD.
+ *
+ * @active_mask must be one of:
+ *  - HRTIMER_ACTIVE_ALL,
+ *  - HRTIMER_ACTIVE_SOFT, or
+ *  - HRTIMER_ACTIVE_HARD.
+ */
+static ktime_t
+__hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask)
+{
+       unsigned int active;
+       struct hrtimer *next_timer = NULL;
+       ktime_t expires_next = KTIME_MAX;
+
+       if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) {
+               active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT;
+               cpu_base->softirq_next_timer = NULL;
+               expires_next = __hrtimer_next_event_base(cpu_base, active, KTIME_MAX);
+
+               next_timer = cpu_base->softirq_next_timer;
+       }
+
+       if (active_mask & HRTIMER_ACTIVE_HARD) {
+               active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD;
+               cpu_base->next_timer = next_timer;
+               expires_next = __hrtimer_next_event_base(cpu_base, active, expires_next);
+       }
+
+       return expires_next;
+}
 
 static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 {
@@ -502,36 +569,14 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
        ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
        ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
 
-       return ktime_get_update_offsets_now(&base->clock_was_set_seq,
+       ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
                                            offs_real, offs_boot, offs_tai);
-}
-
-/* High resolution timer related functions */
-#ifdef CONFIG_HIGH_RES_TIMERS
-
-/*
- * High resolution timer enabled ?
- */
-static bool hrtimer_hres_enabled __read_mostly  = true;
-unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
-EXPORT_SYMBOL_GPL(hrtimer_resolution);
-
-/*
- * Enable / Disable high resolution mode
- */
-static int __init setup_hrtimer_hres(char *str)
-{
-       return (kstrtobool(str, &hrtimer_hres_enabled) == 0);
-}
 
-__setup("highres=", setup_hrtimer_hres);
+       base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
+       base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
+       base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
 
-/*
- * hrtimer_high_res_enabled - query, if the highres mode is enabled
- */
-static inline int hrtimer_is_hres_enabled(void)
-{
-       return hrtimer_hres_enabled;
+       return now;
 }
 
 /*
@@ -539,7 +584,8 @@ static inline int hrtimer_is_hres_enabled(void)
  */
 static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base)
 {
-       return cpu_base->hres_active;
+       return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+               cpu_base->hres_active : 0;
 }
 
 static inline int hrtimer_hres_active(void)
@@ -557,10 +603,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
        ktime_t expires_next;
 
-       if (!cpu_base->hres_active)
-               return;
+       /*
+        * Find the current next expiration time.
+        */
+       expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 
-       expires_next = __hrtimer_get_next_event(cpu_base);
+       if (cpu_base->next_timer && cpu_base->next_timer->is_soft) {
+               /*
+                * When the softirq is activated, hrtimer has to be
+                * programmed with the first hard hrtimer because soft
+                * timer interrupt could occur too late.
+                */
+               if (cpu_base->softirq_activated)
+                       expires_next = __hrtimer_get_next_event(cpu_base,
+                                                               HRTIMER_ACTIVE_HARD);
+               else
+                       cpu_base->softirq_expires_next = expires_next;
+       }
 
        if (skip_equal && expires_next == cpu_base->expires_next)
                return;
@@ -568,6 +627,9 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
        cpu_base->expires_next = expires_next;
 
        /*
+        * If hres is not active, hardware does not have to be
+        * reprogrammed yet.
+        *
         * If a hang was detected in the last timer interrupt then we
         * leave the hang delay active in the hardware. We want the
         * system to make progress. That also prevents the following
@@ -581,83 +643,38 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
         * set. So we'd effectivly block all timers until the T2 event
         * fires.
         */
-       if (cpu_base->hang_detected)
+       if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
                return;
 
        tick_program_event(cpu_base->expires_next, 1);
 }
 
+/* High resolution timer related functions */
+#ifdef CONFIG_HIGH_RES_TIMERS
+
 /*
- * When a timer is enqueued and expires earlier than the already enqueued
- * timers, we have to check, whether it expires earlier than the timer for
- * which the clock event device was armed.
- *
- * Called with interrupts disabled and base->cpu_base.lock held
+ * High resolution timer enabled ?
  */
-static void hrtimer_reprogram(struct hrtimer *timer,
-                             struct hrtimer_clock_base *base)
-{
-       struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-       ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-
-       WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
-
-       /*
-        * If the timer is not on the current cpu, we cannot reprogram
-        * the other cpus clock event device.
-        */
-       if (base->cpu_base != cpu_base)
-               return;
-
-       /*
-        * If the hrtimer interrupt is running, then it will
-        * reevaluate the clock bases and reprogram the clock event
-        * device. The callbacks are always executed in hard interrupt
-        * context so we don't need an extra check for a running
-        * callback.
-        */
-       if (cpu_base->in_hrtirq)
-               return;
-
-       /*
-        * CLOCK_REALTIME timer might be requested with an absolute
-        * expiry time which is less than base->offset. Set it to 0.
-        */
-       if (expires < 0)
-               expires = 0;
-
-       if (expires >= cpu_base->expires_next)
-               return;
-
-       /* Update the pointer to the next expiring timer */
-       cpu_base->next_timer = timer;
-
-       /*
-        * If a hang was detected in the last timer interrupt then we
-        * do not schedule a timer which is earlier than the expiry
-        * which we enforced in the hang detection. We want the system
-        * to make progress.
-        */
-       if (cpu_base->hang_detected)
-               return;
+static bool hrtimer_hres_enabled __read_mostly  = true;
+unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC;
+EXPORT_SYMBOL_GPL(hrtimer_resolution);
 
-       /*
-        * Program the timer hardware. We enforce the expiry for
-        * events which are already in the past.
-        */
-       cpu_base->expires_next = expires;
-       tick_program_event(expires, 1);
+/*
+ * Enable / Disable high resolution mode
+ */
+static int __init setup_hrtimer_hres(char *str)
+{
+       return (kstrtobool(str, &hrtimer_hres_enabled) == 0);
 }
 
+__setup("highres=", setup_hrtimer_hres);
+
 /*
- * Initialize the high resolution related parts of cpu_base
+ * hrtimer_high_res_enabled - query, if the highres mode is enabled
  */
-static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
+static inline int hrtimer_is_hres_enabled(void)
 {
-       base->expires_next = KTIME_MAX;
-       base->hang_detected = 0;
-       base->hres_active = 0;
-       base->next_timer = NULL;
+       return hrtimer_hres_enabled;
 }
 
 /*
@@ -669,7 +686,7 @@ static void retrigger_next_event(void *arg)
 {
        struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
-       if (!base->hres_active)
+       if (!__hrtimer_hres_active(base))
                return;
 
        raw_spin_lock(&base->lock);
@@ -698,6 +715,29 @@ static void hrtimer_switch_to_hres(void)
        retrigger_next_event(NULL);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+static struct swork_event clock_set_delay_work;
+
+static void run_clock_set_delay(struct swork_event *event)
+{
+       clock_was_set();
+}
+
+void clock_was_set_delayed(void)
+{
+       swork_queue(&clock_set_delay_work);
+}
+
+static __init int create_clock_set_delay_thread(void)
+{
+       WARN_ON(swork_get());
+       INIT_SWORK(&clock_set_delay_work, run_clock_set_delay);
+       return 0;
+}
+early_initcall(create_clock_set_delay_thread);
+#else /* PREEMPT_RT_FULL */
+
 static void clock_was_set_work(struct work_struct *work)
 {
        clock_was_set();
@@ -713,25 +753,105 @@ void clock_was_set_delayed(void)
 {
        schedule_work(&hrtimer_work);
 }
+#endif
 
 #else
 
-static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; }
-static inline int hrtimer_hres_active(void) { return 0; }
 static inline int hrtimer_is_hres_enabled(void) { return 0; }
 static inline void hrtimer_switch_to_hres(void) { }
-static inline void
-hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
-static inline int hrtimer_reprogram(struct hrtimer *timer,
-                                   struct hrtimer_clock_base *base)
-{
-       return 0;
-}
-static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
 static inline void retrigger_next_event(void *arg) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
+/*
+ * When a timer is enqueued and expires earlier than the already enqueued
+ * timers, we have to check, whether it expires earlier than the timer for
+ * which the clock event device was armed.
+ *
+ * Called with interrupts disabled and base->cpu_base.lock held
+ */
+static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram)
+{
+       struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+       struct hrtimer_clock_base *base = timer->base;
+       ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+
+       WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
+
+       /*
+        * CLOCK_REALTIME timer might be requested with an absolute
+        * expiry time which is less than base->offset. Set it to 0.
+        */
+       if (expires < 0)
+               expires = 0;
+
+       if (timer->is_soft) {
+               /*
+                * soft hrtimer could be started on a remote CPU. In this
+                * case softirq_expires_next needs to be updated on the
+                * remote CPU. The soft hrtimer will not expire before the
+                * first hard hrtimer on the remote CPU -
+                * hrtimer_check_target() prevents this case.
+                */
+               struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base;
+
+               if (timer_cpu_base->softirq_activated)
+                       return;
+
+               if (!ktime_before(expires, timer_cpu_base->softirq_expires_next))
+                       return;
+
+               timer_cpu_base->softirq_next_timer = timer;
+               timer_cpu_base->softirq_expires_next = expires;
+
+               if (!ktime_before(expires, timer_cpu_base->expires_next) ||
+                   !reprogram)
+                       return;
+       }
+
+       /*
+        * If the timer is not on the current cpu, we cannot reprogram
+        * the other cpus clock event device.
+        */
+       if (base->cpu_base != cpu_base)
+               return;
+
+       /*
+        * If the hrtimer interrupt is running, then it will
+        * reevaluate the clock bases and reprogram the clock event
+        * device. The callbacks are always executed in hard interrupt
+        * context so we don't need an extra check for a running
+        * callback.
+        */
+       if (cpu_base->in_hrtirq)
+               return;
+
+       if (expires >= cpu_base->expires_next)
+               return;
+
+       /* Update the pointer to the next expiring timer */
+       cpu_base->next_timer = timer;
+       cpu_base->expires_next = expires;
+
+       /*
+        * If hres is not active, hardware does not have to be
+        * programmed yet.
+        *
+        * If a hang was detected in the last timer interrupt then we
+        * do not schedule a timer which is earlier than the expiry
+        * which we enforced in the hang detection. We want the system
+        * to make progress.
+        */
+       if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
+               return;
+
+       /*
+        * Program the timer hardware. We enforce the expiry for
+        * events which are already in the past.
+        */
+       tick_program_event(expires, 1);
+}
+
 /*
  * Clock realtime was set
  *
@@ -830,6 +950,33 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 }
 EXPORT_SYMBOL_GPL(hrtimer_forward);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define wake_up_timer_waiters(b)      wake_up(&(b)->wait)
+
+/**
+ * hrtimer_wait_for_timer - Wait for a running timer
+ *
+ * @timer:     timer to wait for
+ *
+ * The function waits in case the timers callback function is
+ * currently executed on the waitqueue of the timer base. The
+ * waitqueue is woken up after the timer callback function has
+ * finished execution.
+ */
+void hrtimer_wait_for_timer(const struct hrtimer *timer)
+{
+       struct hrtimer_clock_base *base = timer->base;
+
+       if (base && base->cpu_base &&
+           base->index >= HRTIMER_BASE_MONOTONIC_SOFT)
+               wait_event(base->cpu_base->wait,
+                               !(hrtimer_callback_running(timer)));
+}
+
+#else
+# define wake_up_timer_waiters(b)      do { } while (0)
+#endif
+
 /*
  * enqueue_hrtimer - internal function to (re)start a timer
  *
@@ -839,9 +986,10 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
  * Returns 1 when the new timer is the leftmost timer in the tree.
  */
 static int enqueue_hrtimer(struct hrtimer *timer,
-                          struct hrtimer_clock_base *base)
+                          struct hrtimer_clock_base *base,
+                          enum hrtimer_mode mode)
 {
-       debug_activate(timer);
+       debug_activate(timer, mode);
 
        base->cpu_base->active_bases |= 1 << base->index;
 
@@ -874,7 +1022,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
        if (!timerqueue_del(&base->active, &timer->node))
                cpu_base->active_bases &= ~(1 << base->index);
 
-#ifdef CONFIG_HIGH_RES_TIMERS
        /*
         * Note: If reprogram is false we do not update
         * cpu_base->next_timer. This happens when we remove the first
@@ -885,7 +1032,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
         */
        if (reprogram && timer == cpu_base->next_timer)
                hrtimer_force_reprogram(cpu_base, 1);
-#endif
 }
 
 /*
@@ -934,22 +1080,36 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
        return tim;
 }
 
-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer:     the timer to be added
- * @tim:       expiry time
- * @delta_ns:  "slack" range for the timer
- * @mode:      expiry mode: absolute (HRTIMER_MODE_ABS) or
- *             relative (HRTIMER_MODE_REL)
- */
-void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
-                           u64 delta_ns, const enum hrtimer_mode mode)
+static void
+hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram)
 {
-       struct hrtimer_clock_base *base, *new_base;
-       unsigned long flags;
-       int leftmost;
+       ktime_t expires;
 
-       base = lock_hrtimer_base(timer, &flags);
+       /*
+        * Find the next SOFT expiration.
+        */
+       expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT);
+
+       /*
+        * reprogramming needs to be triggered, even if the next soft
+        * hrtimer expires at the same time than the next hard
+        * hrtimer. cpu_base->softirq_expires_next needs to be updated!
+        */
+       if (expires == KTIME_MAX)
+               return;
+
+       /*
+        * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event()
+        * cpu_base->*expires_next is only set by hrtimer_reprogram()
+        */
+       hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram);
+}
+
+static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+                                   u64 delta_ns, const enum hrtimer_mode mode,
+                                   struct hrtimer_clock_base *base)
+{
+       struct hrtimer_clock_base *new_base;
 
        /* Remove an active timer from the queue: */
        remove_hrtimer(timer, base, true);
@@ -964,21 +1124,37 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
        /* Switch the timer base, if necessary: */
        new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
 
-       leftmost = enqueue_hrtimer(timer, new_base);
-       if (!leftmost)
-               goto unlock;
+       return enqueue_hrtimer(timer, new_base, mode);
+}
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer
+ * @timer:     the timer to be added
+ * @tim:       expiry time
+ * @delta_ns:  "slack" range for the timer
+ * @mode:      timer mode: absolute (HRTIMER_MODE_ABS) or
+ *             relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
+ *             softirq based mode is considered for debug purpose only!
+ */
+void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+                           u64 delta_ns, const enum hrtimer_mode mode)
+{
+       struct hrtimer_clock_base *base;
+       unsigned long flags;
+
+       /*
+        * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft
+        * match.
+        */
+#ifndef CONFIG_PREEMPT_RT_BASE
+       WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft);
+#endif
+
+       base = lock_hrtimer_base(timer, &flags);
+
+       if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base))
+               hrtimer_reprogram(timer, true);
 
-       if (!hrtimer_is_hres_active(timer)) {
-               /*
-                * Kick to reschedule the next tick to handle the new timer
-                * on dynticks target.
-                */
-               if (new_base->cpu_base->nohz_active)
-                       wake_up_nohz_cpu(new_base->cpu_base->cpu);
-       } else {
-               hrtimer_reprogram(timer, new_base);
-       }
-unlock:
        unlock_hrtimer_base(timer, &flags);
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
@@ -1035,7 +1211,7 @@ int hrtimer_cancel(struct hrtimer *timer)
 
                if (ret >= 0)
                        return ret;
-               cpu_relax();
+               hrtimer_wait_for_timer(timer);
        }
 }
 EXPORT_SYMBOL_GPL(hrtimer_cancel);
@@ -1076,7 +1252,7 @@ u64 hrtimer_get_next_event(void)
        raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
        if (!__hrtimer_hres_active(cpu_base))
-               expires = __hrtimer_get_next_event(cpu_base);
+               expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
 
        raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
@@ -1099,8 +1275,16 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                           enum hrtimer_mode mode)
 {
-       struct hrtimer_cpu_base *cpu_base;
+       bool softtimer;
        int base;
+       struct hrtimer_cpu_base *cpu_base;
+
+       softtimer = !!(mode & HRTIMER_MODE_SOFT);
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (!softtimer && !(mode & HRTIMER_MODE_HARD))
+               softtimer = true;
+#endif
+       base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
 
        memset(timer, 0, sizeof(struct hrtimer));
 
@@ -1114,7 +1298,8 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
        if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL)
                clock_id = CLOCK_MONOTONIC;
 
-       base = hrtimer_clockid_to_base(clock_id);
+       base += hrtimer_clockid_to_base(clock_id);
+       timer->is_soft = softtimer;
        timer->base = &cpu_base->clock_base[base];
        timerqueue_init(&timer->node);
 }
@@ -1123,7 +1308,13 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
  * hrtimer_init - initialize a timer to the given clock
  * @timer:     the timer to be initialized
  * @clock_id:  the clock to be used
- * @mode:      timer mode abs/rel
+ * @mode:       The modes which are relevant for intitialization:
+ *              HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT,
+ *              HRTIMER_MODE_REL_SOFT
+ *
+ *              The PINNED variants of the above can be handed in,
+ *              but the PINNED bit is ignored as pinning happens
+ *              when the hrtimer is started
  */
 void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                  enum hrtimer_mode mode)
@@ -1142,19 +1333,19 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
  */
 bool hrtimer_active(const struct hrtimer *timer)
 {
-       struct hrtimer_cpu_base *cpu_base;
+       struct hrtimer_clock_base *base;
        unsigned int seq;
 
        do {
-               cpu_base = READ_ONCE(timer->base->cpu_base);
-               seq = raw_read_seqcount_begin(&cpu_base->seq);
+               base = READ_ONCE(timer->base);
+               seq = raw_read_seqcount_begin(&base->seq);
 
                if (timer->state != HRTIMER_STATE_INACTIVE ||
-                   cpu_base->running == timer)
+                   base->running == timer)
                        return true;
 
-       } while (read_seqcount_retry(&cpu_base->seq, seq) ||
-                cpu_base != READ_ONCE(timer->base->cpu_base));
+       } while (read_seqcount_retry(&base->seq, seq) ||
+                base != READ_ONCE(timer->base));
 
        return false;
 }
@@ -1180,7 +1371,8 @@ EXPORT_SYMBOL_GPL(hrtimer_active);
 
 static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
                          struct hrtimer_clock_base *base,
-                         struct hrtimer *timer, ktime_t *now)
+                         struct hrtimer *timer, ktime_t *now,
+                         unsigned long flags)
 {
        enum hrtimer_restart (*fn)(struct hrtimer *);
        int restart;
@@ -1188,16 +1380,16 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
        lockdep_assert_held(&cpu_base->lock);
 
        debug_deactivate(timer);
-       cpu_base->running = timer;
+       base->running = timer;
 
        /*
         * Separate the ->running assignment from the ->state assignment.
         *
         * As with a regular write barrier, this ensures the read side in
-        * hrtimer_active() cannot observe cpu_base->running == NULL &&
+        * hrtimer_active() cannot observe base->running == NULL &&
         * timer->state == INACTIVE.
         */
-       raw_write_seqcount_barrier(&cpu_base->seq);
+       raw_write_seqcount_barrier(&base->seq);
 
        __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
        fn = timer->function;
@@ -1211,15 +1403,15 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
                timer->is_rel = false;
 
        /*
-        * Because we run timers from hardirq context, there is no chance
-        * they get migrated to another cpu, therefore its safe to unlock
-        * the timer base.
+        * The timer is marked as running in the cpu base, so it is
+        * protected against migration to a different CPU even if the lock
+        * is dropped.
         */
-       raw_spin_unlock(&cpu_base->lock);
+       raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
        trace_hrtimer_expire_entry(timer, now);
        restart = fn(timer);
        trace_hrtimer_expire_exit(timer);
-       raw_spin_lock(&cpu_base->lock);
+       raw_spin_lock_irq(&cpu_base->lock);
 
        /*
         * Note: We clear the running state after enqueue_hrtimer and
@@ -1232,33 +1424,31 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
         */
        if (restart != HRTIMER_NORESTART &&
            !(timer->state & HRTIMER_STATE_ENQUEUED))
-               enqueue_hrtimer(timer, base);
+               enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS);
 
        /*
         * Separate the ->running assignment from the ->state assignment.
         *
         * As with a regular write barrier, this ensures the read side in
-        * hrtimer_active() cannot observe cpu_base->running == NULL &&
+        * hrtimer_active() cannot observe base->running.timer == NULL &&
         * timer->state == INACTIVE.
         */
-       raw_write_seqcount_barrier(&cpu_base->seq);
+       raw_write_seqcount_barrier(&base->seq);
 
-       WARN_ON_ONCE(cpu_base->running != timer);
-       cpu_base->running = NULL;
+       WARN_ON_ONCE(base->running != timer);
+       base->running = NULL;
 }
 
-static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
+static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now,
+                                unsigned long flags, unsigned int active_mask)
 {
-       struct hrtimer_clock_base *base = cpu_base->clock_base;
-       unsigned int active = cpu_base->active_bases;
+       struct hrtimer_clock_base *base;
+       unsigned int active = cpu_base->active_bases & active_mask;
 
-       for (; active; base++, active >>= 1) {
+       for_each_active_base(base, cpu_base, active) {
                struct timerqueue_node *node;
                ktime_t basenow;
 
-               if (!(active & 0x01))
-                       continue;
-
                basenow = ktime_add(now, base->offset);
 
                while ((node = timerqueue_getnext(&base->active))) {
@@ -1281,11 +1471,29 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
                        if (basenow < hrtimer_get_softexpires_tv64(timer))
                                break;
 
-                       __run_hrtimer(cpu_base, base, timer, &basenow);
+                       __run_hrtimer(cpu_base, base, timer, &basenow, flags);
                }
        }
 }
 
+static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h)
+{
+       struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+       unsigned long flags;
+       ktime_t now;
+
+       raw_spin_lock_irqsave(&cpu_base->lock, flags);
+
+       now = hrtimer_update_base(cpu_base);
+       __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT);
+
+       cpu_base->softirq_activated = 0;
+       hrtimer_update_softirq_timer(cpu_base, true);
+
+       raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+       wake_up_timer_waiters(cpu_base);
+}
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 
 /*
@@ -1296,13 +1504,14 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 {
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
        ktime_t expires_next, now, entry_time, delta;
+       unsigned long flags;
        int retries = 0;
 
        BUG_ON(!cpu_base->hres_active);
        cpu_base->nr_events++;
        dev->next_event = KTIME_MAX;
 
-       raw_spin_lock(&cpu_base->lock);
+       raw_spin_lock_irqsave(&cpu_base->lock, flags);
        entry_time = now = hrtimer_update_base(cpu_base);
 retry:
        cpu_base->in_hrtirq = 1;
@@ -1315,17 +1524,23 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         */
        cpu_base->expires_next = KTIME_MAX;
 
-       __hrtimer_run_queues(cpu_base, now);
+       if (!ktime_before(now, cpu_base->softirq_expires_next)) {
+               cpu_base->softirq_expires_next = KTIME_MAX;
+               cpu_base->softirq_activated = 1;
+               raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+       }
+
+       __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
 
        /* Reevaluate the clock bases for the next expiry */
-       expires_next = __hrtimer_get_next_event(cpu_base);
+       expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
        /*
         * Store the new expiry value so the migration code can verify
         * against it.
         */
        cpu_base->expires_next = expires_next;
        cpu_base->in_hrtirq = 0;
-       raw_spin_unlock(&cpu_base->lock);
+       raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
        /* Reprogramming necessary ? */
        if (!tick_program_event(expires_next, 0)) {
@@ -1346,7 +1561,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         * Acquire base lock for updating the offsets and retrieving
         * the current time.
         */
-       raw_spin_lock(&cpu_base->lock);
+       raw_spin_lock_irqsave(&cpu_base->lock, flags);
        now = hrtimer_update_base(cpu_base);
        cpu_base->nr_retries++;
        if (++retries < 3)
@@ -1359,7 +1574,8 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         */
        cpu_base->nr_hangs++;
        cpu_base->hang_detected = 1;
-       raw_spin_unlock(&cpu_base->lock);
+       raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+
        delta = ktime_sub(now, entry_time);
        if ((unsigned int)delta > cpu_base->max_hang_time)
                cpu_base->max_hang_time = (unsigned int) delta;
@@ -1401,6 +1617,7 @@ static inline void __hrtimer_peek_ahead_timers(void) { }
 void hrtimer_run_queues(void)
 {
        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+       unsigned long flags;
        ktime_t now;
 
        if (__hrtimer_hres_active(cpu_base))
@@ -1418,10 +1635,17 @@ void hrtimer_run_queues(void)
                return;
        }
 
-       raw_spin_lock(&cpu_base->lock);
+       raw_spin_lock_irqsave(&cpu_base->lock, flags);
        now = hrtimer_update_base(cpu_base);
-       __hrtimer_run_queues(cpu_base, now);
-       raw_spin_unlock(&cpu_base->lock);
+
+       if (!ktime_before(now, cpu_base->softirq_expires_next)) {
+               cpu_base->softirq_expires_next = KTIME_MAX;
+               cpu_base->softirq_activated = 1;
+               raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+       }
+
+       __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
+       raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 }
 
 /*
@@ -1440,13 +1664,65 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
        return HRTIMER_NORESTART;
 }
 
-void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
+#ifdef CONFIG_PREEMPT_RT_FULL
+static bool task_is_realtime(struct task_struct *tsk)
 {
+       int policy = tsk->policy;
+
+       if (policy == SCHED_FIFO || policy == SCHED_RR)
+               return true;
+       if (policy == SCHED_DEADLINE)
+               return true;
+       return false;
+}
+#endif
+
+static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
+                                  clockid_t clock_id,
+                                  enum hrtimer_mode mode,
+                                  struct task_struct *task)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (!(mode & (HRTIMER_MODE_SOFT | HRTIMER_MODE_HARD))) {
+               if (task_is_realtime(current) || system_state != SYSTEM_RUNNING)
+                       mode |= HRTIMER_MODE_HARD;
+               else
+                       mode |= HRTIMER_MODE_SOFT;
+       }
+#endif
+       __hrtimer_init(&sl->timer, clock_id, mode);
        sl->timer.function = hrtimer_wakeup;
        sl->task = task;
 }
+
+/**
+ * hrtimer_init_sleeper - initialize sleeper to the given clock
+ * @sl:                sleeper to be initialized
+ * @clock_id:  the clock to be used
+ * @mode:      timer mode abs/rel
+ * @task:      the task to wake up
+ */
+void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
+                         enum hrtimer_mode mode, struct task_struct *task)
+{
+       debug_init(&sl->timer, clock_id, mode);
+       __hrtimer_init_sleeper(sl, clock_id, mode, task);
+
+}
 EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
 
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+                                  clockid_t clock_id,
+                                  enum hrtimer_mode mode,
+                                  struct task_struct *task)
+{
+       debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr);
+       __hrtimer_init_sleeper(sl, clock_id, mode, task);
+}
+EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack);
+#endif
+
 int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
 {
        switch(restart->nanosleep.type) {
@@ -1470,8 +1746,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 {
        struct restart_block *restart;
 
-       hrtimer_init_sleeper(t, current);
-
        do {
                set_current_state(TASK_INTERRUPTIBLE);
                hrtimer_start_expires(&t->timer, mode);
@@ -1508,10 +1782,9 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
        struct hrtimer_sleeper t;
        int ret;
 
-       hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid,
-                               HRTIMER_MODE_ABS);
+       hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid,
+                                     HRTIMER_MODE_ABS, current);
        hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
-
        ret = do_nanosleep(&t, HRTIMER_MODE_ABS);
        destroy_hrtimer_on_stack(&t.timer);
        return ret;
@@ -1529,7 +1802,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp,
        if (dl_task(current) || rt_task(current))
                slack = 0;
 
-       hrtimer_init_on_stack(&t.timer, clockid, mode);
+       hrtimer_init_sleeper_on_stack(&t, clockid, mode, current);
        hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
        ret = do_nanosleep(&t, mode);
        if (ret != -ERESTART_RESTARTBLOCK)
@@ -1585,6 +1858,27 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 }
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * Sleep for 1 ms in hope whoever holds what we want will let it go.
+ */
+void cpu_chill(void)
+{
+       ktime_t chill_time;
+       unsigned int freeze_flag = current->flags & PF_NOFREEZE;
+
+       chill_time = ktime_set(0, NSEC_PER_MSEC);
+       set_current_state(TASK_UNINTERRUPTIBLE);
+       current->flags |= PF_NOFREEZE;
+       sleeping_lock_inc();
+       schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD);
+       sleeping_lock_dec();
+       if (!freeze_flag)
+               current->flags &= ~PF_NOFREEZE;
+}
+EXPORT_SYMBOL(cpu_chill);
+#endif
+
 /*
  * Functions related to boot-time initialization:
  */
@@ -1598,9 +1892,17 @@ int hrtimers_prepare_cpu(unsigned int cpu)
                timerqueue_init_head(&cpu_base->clock_base[i].active);
        }
 
-       cpu_base->active_bases = 0;
        cpu_base->cpu = cpu;
-       hrtimer_init_hres(cpu_base);
+       cpu_base->active_bases = 0;
+       cpu_base->hres_active = 0;
+       cpu_base->hang_detected = 0;
+       cpu_base->next_timer = NULL;
+       cpu_base->softirq_next_timer = NULL;
+       cpu_base->expires_next = KTIME_MAX;
+       cpu_base->softirq_expires_next = KTIME_MAX;
+#ifdef CONFIG_PREEMPT_RT_BASE
+       init_waitqueue_head(&cpu_base->wait);
+#endif
        return 0;
 }
 
@@ -1632,7 +1934,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                 * sort out already expired timers and reprogram the
                 * event device.
                 */
-               enqueue_hrtimer(timer, new_base);
+               enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS);
        }
 }
 
@@ -1644,6 +1946,12 @@ int hrtimers_dead_cpu(unsigned int scpu)
        BUG_ON(cpu_online(scpu));
        tick_cancel_sched_timer(scpu);
 
+       /*
+        * this BH disable ensures that raise_softirq_irqoff() does
+        * not wakeup ksoftirqd (and acquire the pi-lock) while
+        * holding the cpu_base lock
+        */
+       local_bh_disable();
        local_irq_disable();
        old_base = &per_cpu(hrtimer_bases, scpu);
        new_base = this_cpu_ptr(&hrtimer_bases);
@@ -1659,12 +1967,19 @@ int hrtimers_dead_cpu(unsigned int scpu)
                                     &new_base->clock_base[i]);
        }
 
+       /*
+        * The migration might have changed the first expiring softirq
+        * timer on this CPU. Update it.
+        */
+       hrtimer_update_softirq_timer(new_base, false);
+
        raw_spin_unlock(&old_base->lock);
        raw_spin_unlock(&new_base->lock);
 
        /* Check, if we got expired work to do */
        __hrtimer_peek_ahead_timers();
        local_irq_enable();
+       local_bh_enable();
        return 0;
 }
 
@@ -1673,18 +1988,19 @@ int hrtimers_dead_cpu(unsigned int scpu)
 void __init hrtimers_init(void)
 {
        hrtimers_prepare_cpu(smp_processor_id());
+       open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq);
 }
 
 /**
  * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:   timeout value (ktime_t)
  * @delta:     slack in expires timeout (ktime_t)
- * @mode:      timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
- * @clock:     timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
+ * @mode:      timer mode
+ * @clock_id:  timer clock to be used
  */
 int __sched
 schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
-                              const enum hrtimer_mode mode, int clock)
+                              const enum hrtimer_mode mode, clockid_t clock_id)
 {
        struct hrtimer_sleeper t;
 
@@ -1705,11 +2021,9 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
                return -EINTR;
        }
 
-       hrtimer_init_on_stack(&t.timer, clock, mode);
+       hrtimer_init_sleeper_on_stack(&t, clock_id, mode, current);
        hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
-       hrtimer_init_sleeper(&t, current);
-
        hrtimer_start_expires(&t.timer, mode);
 
        if (likely(t.task))
@@ -1727,7 +2041,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
  * schedule_hrtimeout_range - sleep until timeout
  * @expires:   timeout value (ktime_t)
  * @delta:     slack in expires timeout (ktime_t)
- * @mode:      timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ * @mode:      timer mode
  *
  * Make the current task sleep until the given expiry time has
  * elapsed. The routine will return immediately unless
@@ -1766,7 +2080,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
 /**
  * schedule_hrtimeout - sleep until timeout
  * @expires:   timeout value (ktime_t)
- * @mode:      timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ * @mode:      timer mode
  *
  * Make the current task sleep until the given expiry time has
  * elapsed. The routine will return immediately unless
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index f26acef5d7b4..760f38528365 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -214,6 +214,7 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
                /* We are sharing ->siglock with it_real_fn() */
                if (hrtimer_try_to_cancel(timer) < 0) {
                        spin_unlock_irq(&tsk->sighand->siglock);
+                       hrtimer_wait_for_timer(&tsk->signal->real_timer);
                        goto again;
                }
                expires = timeval_to_ktime(value->it_value);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 497719127bf9..62acb8914c9e 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -74,7 +74,8 @@ static struct clocksource clocksource_jiffies = {
        .max_cycles     = 10,
 };
 
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
+__cacheline_aligned_in_smp seqcount_t jiffies_seq;
 
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
@@ -83,9 +84,9 @@ u64 get_jiffies_64(void)
        u64 ret;
 
        do {
-               seq = read_seqbegin(&jiffies_lock);
+               seq = read_seqcount_begin(&jiffies_seq);
                ret = jiffies_64;
-       } while (read_seqretry(&jiffies_lock, seq));
+       } while (read_seqcount_retry(&jiffies_seq, seq));
        return ret;
 }
 EXPORT_SYMBOL(get_jiffies_64);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 2da660d53a4b..c7b7d047d12e 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -3,8 +3,10 @@
  * Implement CPU time clocks for the POSIX clock interface.
  */
 
+#include <uapi/linux/sched/types.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/rt.h>
 #include <linux/posix-timers.h>
 #include <linux/errno.h>
 #include <linux/math64.h>
@@ -14,6 +16,7 @@
 #include <linux/tick.h>
 #include <linux/workqueue.h>
 #include <linux/compat.h>
+#include <linux/smpboot.h>
 
 #include "posix-timers.h"
 
@@ -603,7 +606,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
        /*
         * Disarm any old timer after extracting its expiry time.
         */
-       WARN_ON_ONCE(!irqs_disabled());
+       WARN_ON_ONCE_NONRT(!irqs_disabled());
 
        ret = 0;
        old_incr = timer->it.cpu.incr;
@@ -1034,7 +1037,7 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
        /*
         * Now re-arm for the new expiry time.
         */
-       WARN_ON_ONCE(!irqs_disabled());
+       WARN_ON_ONCE_NONRT(!irqs_disabled());
        arm_timer(timer);
 unlock:
        unlock_task_sighand(p, &flags);
@@ -1119,13 +1122,13 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
  * already updated our counts.  We need to check if any timers fire now.
  * Interrupts are disabled.
  */
-void run_posix_cpu_timers(struct task_struct *tsk)
+static void __run_posix_cpu_timers(struct task_struct *tsk)
 {
        LIST_HEAD(firing);
        struct k_itimer *timer, *next;
        unsigned long flags;
 
-       WARN_ON_ONCE(!irqs_disabled());
+       WARN_ON_ONCE_NONRT(!irqs_disabled());
 
        /*
         * The fast path checks that there are no expired thread or thread
@@ -1179,6 +1182,152 @@ void run_posix_cpu_timers(struct task_struct *tsk)
        }
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+#include <linux/kthread.h>
+#include <linux/cpu.h>
+DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
+DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
+DEFINE_PER_CPU(bool, posix_timer_th_active);
+
+static void posix_cpu_kthread_fn(unsigned int cpu)
+{
+       struct task_struct *tsk = NULL;
+       struct task_struct *next = NULL;
+
+       BUG_ON(per_cpu(posix_timer_task, cpu) != current);
+
+       /* grab task list */
+       raw_local_irq_disable();
+       tsk = per_cpu(posix_timer_tasklist, cpu);
+       per_cpu(posix_timer_tasklist, cpu) = NULL;
+       raw_local_irq_enable();
+
+       /* its possible the list is empty, just return */
+       if (!tsk)
+               return;
+
+       /* Process task list */
+       while (1) {
+               /* save next */
+               next = tsk->posix_timer_list;
+
+               /* run the task timers, clear its ptr and
+                * unreference it
+                */
+               __run_posix_cpu_timers(tsk);
+               tsk->posix_timer_list = NULL;
+               put_task_struct(tsk);
+
+               /* check if this is the last on the list */
+               if (next == tsk)
+                       break;
+               tsk = next;
+       }
+}
+
+static inline int __fastpath_timer_check(struct task_struct *tsk)
+{
+       /* tsk == current, ensure it is safe to use ->signal/sighand */
+       if (unlikely(tsk->exit_state))
+               return 0;
+
+       if (!task_cputime_zero(&tsk->cputime_expires))
+                       return 1;
+
+       if (!task_cputime_zero(&tsk->signal->cputime_expires))
+                       return 1;
+
+       return 0;
+}
+
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+       unsigned int cpu = smp_processor_id();
+       struct task_struct *tasklist;
+
+       BUG_ON(!irqs_disabled());
+
+       if (per_cpu(posix_timer_th_active, cpu) != true)
+               return;
+
+       /* get per-cpu references */
+       tasklist = per_cpu(posix_timer_tasklist, cpu);
+
+       /* check to see if we're already queued */
+       if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) {
+               get_task_struct(tsk);
+               if (tasklist) {
+                       tsk->posix_timer_list = tasklist;
+               } else {
+                       /*
+                        * The list is terminated by a self-pointing
+                        * task_struct
+                        */
+                       tsk->posix_timer_list = tsk;
+               }
+               per_cpu(posix_timer_tasklist, cpu) = tsk;
+
+               wake_up_process(per_cpu(posix_timer_task, cpu));
+       }
+}
+
+static int posix_cpu_kthread_should_run(unsigned int cpu)
+{
+       return __this_cpu_read(posix_timer_tasklist) != NULL;
+}
+
+static void posix_cpu_kthread_park(unsigned int cpu)
+{
+       this_cpu_write(posix_timer_th_active, false);
+}
+
+static void posix_cpu_kthread_unpark(unsigned int cpu)
+{
+       this_cpu_write(posix_timer_th_active, true);
+}
+
+static void posix_cpu_kthread_setup(unsigned int cpu)
+{
+       struct sched_param sp;
+
+       sp.sched_priority = MAX_RT_PRIO - 1;
+       sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+       posix_cpu_kthread_unpark(cpu);
+}
+
+static struct smp_hotplug_thread posix_cpu_thread = {
+       .store                  = &posix_timer_task,
+       .thread_should_run      = posix_cpu_kthread_should_run,
+       .thread_fn              = posix_cpu_kthread_fn,
+       .thread_comm            = "posixcputmr/%u",
+       .setup                  = posix_cpu_kthread_setup,
+       .park                   = posix_cpu_kthread_park,
+       .unpark                 = posix_cpu_kthread_unpark,
+};
+
+static int __init posix_cpu_thread_init(void)
+{
+       /* Start one for boot CPU. */
+       unsigned long cpu;
+       int ret;
+
+       /* init the per-cpu posix_timer_tasklets */
+       for_each_possible_cpu(cpu)
+               per_cpu(posix_timer_tasklist, cpu) = NULL;
+
+       ret = smpboot_register_percpu_thread(&posix_cpu_thread);
+       WARN_ON(ret);
+
+       return 0;
+}
+early_initcall(posix_cpu_thread_init);
+#else /* CONFIG_PREEMPT_RT_BASE */
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+       __run_posix_cpu_timers(tsk);
+}
+#endif /* CONFIG_PREEMPT_RT_BASE */
+
 /*
  * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 55d45fe2cc17..5a59538f3d16 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -443,6 +443,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 static struct pid *good_sigevent(sigevent_t * event)
 {
        struct task_struct *rtn = current->group_leader;
+       int sig = event->sigev_signo;
 
        switch (event->sigev_notify) {
        case SIGEV_SIGNAL | SIGEV_THREAD_ID:
@@ -452,7 +453,8 @@ static struct pid *good_sigevent(sigevent_t * event)
                /* FALLTHRU */
        case SIGEV_SIGNAL:
        case SIGEV_THREAD:
-               if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
+               if (sig <= 0 || sig > SIGRTMAX ||
+                   sig_kernel_only(sig) || sig_kernel_coredump(sig))
                        return NULL;
                /* FALLTHRU */
        case SIGEV_NONE:
@@ -478,7 +480,7 @@ static struct k_itimer * alloc_posix_timer(void)
 
 static void k_itimer_rcu_free(struct rcu_head *head)
 {
-       struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);
+       struct k_itimer *tmr = container_of(head, struct k_itimer, rcu);
 
        kmem_cache_free(posix_timers_cache, tmr);
 }
@@ -495,7 +497,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
        }
        put_pid(tmr->it_pid);
        sigqueue_free(tmr->sigq);
-       call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
+       call_rcu(&tmr->rcu, k_itimer_rcu_free);
 }
 
 static int common_timer_create(struct k_itimer *new_timer)
@@ -834,6 +836,22 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires,
                hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/*
+ * Protected by RCU!
+ */
+static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timr)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (kc->timer_arm == common_hrtimer_arm)
+               hrtimer_wait_for_timer(&timr->it.real.timer);
+       else if (kc == &alarm_clock)
+               hrtimer_wait_for_timer(&timr->it.alarm.alarmtimer.timer);
+       else
+               /* FIXME: Whacky hack for posix-cpu-timers */
+               schedule_timeout(1);
+#endif
+}
+
 static int common_hrtimer_try_to_cancel(struct k_itimer *timr)
 {
        return hrtimer_try_to_cancel(&timr->it.real.timer);
@@ -898,6 +916,7 @@ static int do_timer_settime(timer_t timer_id, int flags,
        if (!timr)
                return -EINVAL;
 
+       rcu_read_lock();
        kc = timr->kclock;
        if (WARN_ON_ONCE(!kc || !kc->timer_set))
                error = -EINVAL;
@@ -906,9 +925,12 @@ static int do_timer_settime(timer_t timer_id, int flags,
 
        unlock_timer(timr, flag);
        if (error == TIMER_RETRY) {
+               timer_wait_for_callback(kc, timr);
                old_spec64 = NULL;      // We already got the old time...
+               rcu_read_unlock();
                goto retry;
        }
+       rcu_read_unlock();
 
        return error;
 }
@@ -990,10 +1012,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
        if (!timer)
                return -EINVAL;
 
+       rcu_read_lock();
        if (timer_delete_hook(timer) == TIMER_RETRY) {
                unlock_timer(timer, flags);
+               timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+                                       timer);
+               rcu_read_unlock();
                goto retry_delete;
        }
+       rcu_read_unlock();
 
        spin_lock(&current->sighand->siglock);
        list_del(&timer->list);
@@ -1019,8 +1046,18 @@ static void itimer_delete(struct k_itimer *timer)
 retry_delete:
        spin_lock_irqsave(&timer->it_lock, flags);
 
+       /* On RT we can race with a deletion */
+       if (!timer->it_signal) {
+               unlock_timer(timer, flags);
+               return;
+       }
+
        if (timer_delete_hook(timer) == TIMER_RETRY) {
+               rcu_read_lock();
                unlock_timer(timer, flags);
+               timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+                                       timer);
+               rcu_read_unlock();
                goto retry_delete;
        }
        list_del(&timer->list);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 58045eb976c3..f0a34afbc252 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -106,7 +106,7 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 
 void tick_setup_hrtimer_broadcast(void)
 {
-       hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+       hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
        bctimer.function = bc_handler;
        clockevents_register_device(&ce_broadcast_hrtimer);
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 49edc1c4f3e6..7a87a4488a5e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -79,13 +79,15 @@ int tick_is_oneshot_available(void)
 static void tick_periodic(int cpu)
 {
        if (tick_do_timer_cpu == cpu) {
-               write_seqlock(&jiffies_lock);
+               raw_spin_lock(&jiffies_lock);
+               write_seqcount_begin(&jiffies_seq);
 
                /* Keep track of the next tick event */
                tick_next_period = ktime_add(tick_next_period, tick_period);
 
                do_timer(1);
-               write_sequnlock(&jiffies_lock);
+               write_seqcount_end(&jiffies_seq);
+               raw_spin_unlock(&jiffies_lock);
                update_wall_time();
        }
 
@@ -157,9 +159,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
                ktime_t next;
 
                do {
-                       seq = read_seqbegin(&jiffies_lock);
+                       seq = read_seqcount_begin(&jiffies_seq);
                        next = tick_next_period;
-               } while (read_seqretry(&jiffies_lock, seq));
+               } while (read_seqcount_retry(&jiffies_seq, seq));
 
                clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
@@ -490,6 +492,7 @@ void tick_freeze(void)
        if (tick_freeze_depth == num_online_cpus()) {
                trace_suspend_resume(TPS("timekeeping_freeze"),
                                     smp_processor_id(), true);
+               system_state = SYSTEM_SUSPEND;
                timekeeping_suspend();
        } else {
                tick_suspend_local();
@@ -513,6 +516,7 @@ void tick_unfreeze(void)
 
        if (tick_freeze_depth == num_online_cpus()) {
                timekeeping_resume();
+               system_state = SYSTEM_RUNNING;
                trace_suspend_resume(TPS("timekeeping_freeze"),
                                     smp_processor_id(), false);
        } else {
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f8e1845aa464..e277284c2831 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -150,16 +150,15 @@ static inline void tick_nohz_init(void) { }
 
 #ifdef CONFIG_NO_HZ_COMMON
 extern unsigned long tick_nohz_active;
-#else
+extern void timers_update_nohz(void);
+# ifdef CONFIG_SMP
+extern struct static_key_false timers_migration_enabled;
+# endif
+#else /* CONFIG_NO_HZ_COMMON */
+static inline void timers_update_nohz(void) { }
 #define tick_nohz_active (0)
 #endif
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void timers_update_migration(bool update_nohz);
-#else
-static inline void timers_update_migration(bool update_nohz) { }
-#endif
-
 DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
 
 extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a8fa0a896b78..643b36a0b8e1 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -66,7 +66,8 @@ static void tick_do_update_jiffies64(ktime_t now)
                return;
 
        /* Reevaluate with jiffies_lock held */
-       write_seqlock(&jiffies_lock);
+       raw_spin_lock(&jiffies_lock);
+       write_seqcount_begin(&jiffies_seq);
 
        delta = ktime_sub(now, last_jiffies_update);
        if (delta >= tick_period) {
@@ -89,10 +90,12 @@ static void tick_do_update_jiffies64(ktime_t now)
                /* Keep the tick_next_period variable up to date */
                tick_next_period = ktime_add(last_jiffies_update, tick_period);
        } else {
-               write_sequnlock(&jiffies_lock);
+               write_seqcount_end(&jiffies_seq);
+               raw_spin_unlock(&jiffies_lock);
                return;
        }
-       write_sequnlock(&jiffies_lock);
+       write_seqcount_end(&jiffies_seq);
+       raw_spin_unlock(&jiffies_lock);
        update_wall_time();
 }
 
@@ -103,12 +106,14 @@ static ktime_t tick_init_jiffy_update(void)
 {
        ktime_t period;
 
-       write_seqlock(&jiffies_lock);
+       raw_spin_lock(&jiffies_lock);
+       write_seqcount_begin(&jiffies_seq);
        /* Did we start the jiffies update yet ? */
        if (last_jiffies_update == 0)
                last_jiffies_update = tick_next_period;
        period = last_jiffies_update;
-       write_sequnlock(&jiffies_lock);
+       write_seqcount_end(&jiffies_seq);
+       raw_spin_unlock(&jiffies_lock);
        return period;
 }
 
@@ -225,6 +230,7 @@ static void nohz_full_kick_func(struct irq_work *work)
 
 static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
        .func = nohz_full_kick_func,
+       .flags = IRQ_WORK_HARD_IRQ,
 };
 
 /*
@@ -689,10 +695,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 
        /* Read jiffies and the time when jiffies were updated last */
        do {
-               seq = read_seqbegin(&jiffies_lock);
+               seq = read_seqcount_begin(&jiffies_seq);
                basemono = last_jiffies_update;
                basejiff = jiffies;
-       } while (read_seqretry(&jiffies_lock, seq));
+       } while (read_seqcount_retry(&jiffies_seq, seq));
        ts->last_jiffies = basejiff;
 
        /*
@@ -906,14 +912,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
                return false;
 
        if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
-               static int ratelimit;
-
-               if (ratelimit < 10 && !in_softirq() &&
-                   (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
-                       pr_warn("NOHZ: local_softirq_pending %02x\n",
-                               (unsigned int) local_softirq_pending());
-                       ratelimit++;
-               }
+               softirq_check_pending_idle();
                return false;
        }
 
@@ -1132,7 +1131,7 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
        ts->nohz_mode = mode;
        /* One update is enough */
        if (!test_and_set_bit(0, &tick_nohz_active))
-               timers_update_migration(true);
+               timers_update_nohz();
 }
 
 /**
@@ -1250,7 +1249,7 @@ void tick_setup_sched_timer(void)
        /*
         * Emulate tick processing via per-CPU hrtimers:
         */
-       hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+       hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
        ts->sched_timer.function = tick_sched_timer;
 
        /* Get the next period (per-CPU) */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2cafb49aa65e..2720f2c29a6d 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2326,8 +2326,10 @@ EXPORT_SYMBOL(hardpps);
  */
 void xtime_update(unsigned long ticks)
 {
-       write_seqlock(&jiffies_lock);
+       raw_spin_lock(&jiffies_lock);
+       write_seqcount_begin(&jiffies_seq);
        do_timer(ticks);
-       write_sequnlock(&jiffies_lock);
+       write_seqcount_end(&jiffies_seq);
+       raw_spin_unlock(&jiffies_lock);
        update_wall_time();
 }
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index c9f9af339914..0c0f52bf1927 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -18,7 +18,8 @@ extern void timekeeping_resume(void);
 extern void do_timer(unsigned long ticks);
 extern void update_wall_time(void);
 
-extern seqlock_t jiffies_lock;
+extern raw_spinlock_t jiffies_lock;
+extern seqcount_t jiffies_seq;
 
 #define CS_NAME_LEN    32
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index f17c76a1a05f..5fadd754ce20 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -44,6 +44,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/swait.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -197,11 +198,12 @@ EXPORT_SYMBOL(jiffies_64);
 struct timer_base {
        raw_spinlock_t          lock;
        struct timer_list       *running_timer;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct swait_queue_head wait_for_running_timer;
+#endif
        unsigned long           clk;
        unsigned long           next_expiry;
        unsigned int            cpu;
-       bool                    migration_enabled;
-       bool                    nohz_active;
        bool                    is_idle;
        bool                    must_forward_clk;
        DECLARE_BITMAP(pending_map, WHEEL_SIZE);
@@ -210,45 +212,73 @@ struct timer_base {
 
 static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]);
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
+
+static DEFINE_STATIC_KEY_FALSE(timers_nohz_active);
+static DEFINE_MUTEX(timer_keys_mutex);
+
+static struct swork_event timer_update_swork;
+
+#ifdef CONFIG_SMP
 unsigned int sysctl_timer_migration = 1;
 
-void timers_update_migration(bool update_nohz)
+DEFINE_STATIC_KEY_FALSE(timers_migration_enabled);
+
+static void timers_update_migration(void)
 {
        bool on = sysctl_timer_migration && tick_nohz_active;
-       unsigned int cpu;
 
-       /* Avoid the loop, if nothing to update */
-       if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on)
-               return;
+       if (on)
+               static_branch_enable(&timers_migration_enabled);
+       else
+               static_branch_disable(&timers_migration_enabled);
+}
+#else
+static inline void timers_update_migration(void) { }
+#endif /* !CONFIG_SMP */
 
-       for_each_possible_cpu(cpu) {
-               per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on;
-               per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on;
-               per_cpu(hrtimer_bases.migration_enabled, cpu) = on;
-               if (!update_nohz)
-                       continue;
-               per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true;
-               per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true;
-               per_cpu(hrtimer_bases.nohz_active, cpu) = true;
-       }
+static void timer_update_keys(struct swork_event *event)
+{
+       mutex_lock(&timer_keys_mutex);
+       timers_update_migration();
+       static_branch_enable(&timers_nohz_active);
+       mutex_unlock(&timer_keys_mutex);
+}
+
+void timers_update_nohz(void)
+{
+       swork_queue(&timer_update_swork);
+}
+
+static __init int hrtimer_init_thread(void)
+{
+       WARN_ON(swork_get());
+       INIT_SWORK(&timer_update_swork, timer_update_keys);
+       return 0;
 }
+early_initcall(hrtimer_init_thread);
 
 int timer_migration_handler(struct ctl_table *table, int write,
                            void __user *buffer, size_t *lenp,
                            loff_t *ppos)
 {
-       static DEFINE_MUTEX(mutex);
        int ret;
 
-       mutex_lock(&mutex);
+       mutex_lock(&timer_keys_mutex);
        ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
        if (!ret && write)
-               timers_update_migration(false);
-       mutex_unlock(&mutex);
+               timers_update_migration();
+       mutex_unlock(&timer_keys_mutex);
        return ret;
 }
-#endif
+
+static inline bool is_timers_nohz_active(void)
+{
+       return static_branch_unlikely(&timers_nohz_active);
+}
+#else
+static inline bool is_timers_nohz_active(void) { return false; }
+#endif /* NO_HZ_COMMON */
 
 static unsigned long round_jiffies_common(unsigned long j, int cpu,
                bool force_up)
@@ -534,7 +564,7 @@ __internal_add_timer(struct timer_base *base, struct timer_list *timer)
 static void
 trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 {
-       if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+       if (!is_timers_nohz_active())
                return;
 
        /*
@@ -840,21 +870,20 @@ static inline struct timer_base *get_timer_base(u32 tflags)
        return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
 }
 
-#ifdef CONFIG_NO_HZ_COMMON
 static inline struct timer_base *
 get_target_base(struct timer_base *base, unsigned tflags)
 {
-#ifdef CONFIG_SMP
-       if ((tflags & TIMER_PINNED) || !base->migration_enabled)
-               return get_timer_this_cpu_base(tflags);
-       return get_timer_cpu_base(tflags, get_nohz_timer_target());
-#else
-       return get_timer_this_cpu_base(tflags);
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+       if (static_branch_unlikely(&timers_migration_enabled) &&
+           !(tflags & TIMER_PINNED))
+               return get_timer_cpu_base(tflags, get_nohz_timer_target());
 #endif
+       return get_timer_this_cpu_base(tflags);
 }
 
 static inline void forward_timer_base(struct timer_base *base)
 {
+#ifdef CONFIG_NO_HZ_COMMON
        unsigned long jnow;
 
        /*
@@ -878,16 +907,8 @@ static inline void forward_timer_base(struct timer_base *base)
                base->clk = jnow;
        else
                base->clk = base->next_expiry;
-}
-#else
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
-       return get_timer_this_cpu_base(tflags);
-}
-
-static inline void forward_timer_base(struct timer_base *base) { }
 #endif
+}
 
 
 /*
@@ -1130,6 +1151,33 @@ void add_timer_on(struct timer_list *timer, int cpu)
 }
 EXPORT_SYMBOL_GPL(add_timer_on);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * Wait for a running timer
+ */
+static void wait_for_running_timer(struct timer_list *timer)
+{
+       struct timer_base *base;
+       u32 tf = timer->flags;
+
+       if (tf & TIMER_MIGRATING)
+               return;
+
+       base = get_timer_base(tf);
+       swait_event(base->wait_for_running_timer,
+                   base->running_timer != timer);
+}
+
+# define wakeup_timer_waiters(b)       swake_up_all(&(b)->wait_for_running_timer)
+#else
+static inline void wait_for_running_timer(struct timer_list *timer)
+{
+       cpu_relax();
+}
+
+# define wakeup_timer_waiters(b)       do { } while (0)
+#endif
+
 /**
  * del_timer - deactivate a timer.
  * @timer: the timer to be deactivated
@@ -1185,7 +1233,7 @@ int try_to_del_timer_sync(struct timer_list *timer)
 }
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1245,7 +1293,7 @@ int del_timer_sync(struct timer_list *timer)
                int ret = try_to_del_timer_sync(timer);
                if (ret >= 0)
                        return ret;
-               cpu_relax();
+               wait_for_running_timer(timer);
        }
 }
 EXPORT_SYMBOL(del_timer_sync);
@@ -1309,13 +1357,16 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
                fn = timer->function;
                data = timer->data;
 
-               if (timer->flags & TIMER_IRQSAFE) {
+               if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL) &&
+                   timer->flags & TIMER_IRQSAFE) {
                        raw_spin_unlock(&base->lock);
                        call_timer_fn(timer, fn, data);
+                       base->running_timer = NULL;
                        raw_spin_lock(&base->lock);
                } else {
                        raw_spin_unlock_irq(&base->lock);
                        call_timer_fn(timer, fn, data);
+                       base->running_timer = NULL;
                        raw_spin_lock_irq(&base->lock);
                }
        }
@@ -1586,7 +1637,7 @@ void update_process_times(int user_tick)
        account_process_tick(p, user_tick);
        run_local_timers();
        rcu_check_callbacks(user_tick);
-#ifdef CONFIG_IRQ_WORK
+#if defined(CONFIG_IRQ_WORK)
        if (in_irq())
                irq_work_tick();
 #endif
@@ -1633,8 +1684,8 @@ static inline void __run_timers(struct timer_base *base)
                while (levels--)
                        expire_timers(base, heads + levels);
        }
-       base->running_timer = NULL;
        raw_spin_unlock_irq(&base->lock);
+       wakeup_timer_waiters(base);
 }
 
 /*
@@ -1644,6 +1695,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
        struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
+       irq_work_tick_soft();
        __run_timers(base);
        if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
                __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
@@ -1867,6 +1919,9 @@ static void __init init_timer_cpu(int cpu)
                base->cpu = cpu;
                raw_spin_lock_init(&base->lock);
                base->clk = jiffies;
+#ifdef CONFIG_PREEMPT_RT_FULL
+               init_swait_queue_head(&base->wait_for_running_timer);
+#endif
        }
 }
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 4ad6f6ca18c1..55d39a3fbdf7 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -585,7 +585,10 @@ config HIST_TRIGGERS
          event activity as an initial guide for further investigation
          using more advanced tools.
 
-         See Documentation/trace/events.txt.
+         Inter-event tracing of quantities such as latencies is also
+         supported using hist triggers under this option.
+
+         See Documentation/trace/histogram.txt.
          If in doubt, say N.
 
 config MMIOTRACE_TEST
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a1d5e0949dcf..e8ca1e01facd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -41,6 +41,8 @@ int ring_buffer_print_entry_header(struct trace_seq *s)
                         RINGBUF_TYPE_PADDING);
        trace_seq_printf(s, "\ttime_extend : type == %d\n",
                         RINGBUF_TYPE_TIME_EXTEND);
+       trace_seq_printf(s, "\ttime_stamp : type == %d\n",
+                        RINGBUF_TYPE_TIME_STAMP);
        trace_seq_printf(s, "\tdata max type_len  == %d\n",
                         RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
 
@@ -140,12 +142,15 @@ int ring_buffer_print_entry_header(struct trace_seq *s)
 
 enum {
        RB_LEN_TIME_EXTEND = 8,
-       RB_LEN_TIME_STAMP = 16,
+       RB_LEN_TIME_STAMP =  8,
 };
 
 #define skip_time_extend(event) \
        ((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND))
 
+#define extended_time(event) \
+       (event->type_len >= RINGBUF_TYPE_TIME_EXTEND)
+
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
        return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
@@ -209,7 +214,7 @@ rb_event_ts_length(struct ring_buffer_event *event)
 {
        unsigned len = 0;
 
-       if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+       if (extended_time(event)) {
                /* time extends include the data event after it */
                len = RB_LEN_TIME_EXTEND;
                event = skip_time_extend(event);
@@ -231,7 +236,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
        unsigned length;
 
-       if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+       if (extended_time(event))
                event = skip_time_extend(event);
 
        length = rb_event_length(event);
@@ -248,7 +253,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 static __always_inline void *
 rb_event_data(struct ring_buffer_event *event)
 {
-       if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+       if (extended_time(event))
                event = skip_time_extend(event);
        BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
        /* If length is in len field, then array[0] has the data */
@@ -275,6 +280,27 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define TS_MASK                ((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST  (~TS_MASK)
 
+/**
+ * ring_buffer_event_time_stamp - return the event's extended timestamp
+ * @event: the event to get the timestamp of
+ *
+ * Returns the extended timestamp associated with a data event.
+ * An extended time_stamp is a 64-bit timestamp represented
+ * internally in a special way that makes the best use of space
+ * contained within a ring buffer event.  This function decodes
+ * it and maps it to a straight u64 value.
+ */
+u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event)
+{
+       u64 ts;
+
+       ts = event->array[0];
+       ts <<= TS_SHIFT;
+       ts += event->time_delta;
+
+       return ts;
+}
+
 /* Flag when events were overwritten */
 #define RB_MISSED_EVENTS       (1 << 31)
 /* Missed count stored at end */
@@ -451,6 +477,7 @@ struct ring_buffer_per_cpu {
        struct buffer_page              *reader_page;
        unsigned long                   lost_events;
        unsigned long                   last_overrun;
+       unsigned long                   nest;
        local_t                         entries_bytes;
        local_t                         entries;
        local_t                         overrun;
@@ -488,6 +515,7 @@ struct ring_buffer {
        u64                             (*clock)(void);
 
        struct rb_irq_work              irq_work;
+       bool                            time_stamp_abs;
 };
 
 struct ring_buffer_iter {
@@ -1387,6 +1415,16 @@ void ring_buffer_set_clock(struct ring_buffer *buffer,
        buffer->clock = clock;
 }
 
+void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs)
+{
+       buffer->time_stamp_abs = abs;
+}
+
+bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer)
+{
+       return buffer->time_stamp_abs;
+}
+
 static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
 
 static inline unsigned long rb_page_entries(struct buffer_page *bpage)
@@ -2219,12 +2257,15 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 
 /* Slow path, do not inline */
 static noinline struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
+rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 {
-       event->type_len = RINGBUF_TYPE_TIME_EXTEND;
+       if (abs)
+               event->type_len = RINGBUF_TYPE_TIME_STAMP;
+       else
+               event->type_len = RINGBUF_TYPE_TIME_EXTEND;
 
-       /* Not the first event on the page? */
-       if (rb_event_index(event)) {
+       /* Not the first event on the page, or not delta? */
+       if (abs || rb_event_index(event)) {
                event->time_delta = delta & TS_MASK;
                event->array[0] = delta >> TS_SHIFT;
        } else {
@@ -2267,7 +2308,9 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
         * add it to the start of the resevered space.
         */
        if (unlikely(info->add_timestamp)) {
-               event = rb_add_time_stamp(event, delta);
+               bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
+
+               event = rb_add_time_stamp(event, info->delta, abs);
                length -= RB_LEN_TIME_EXTEND;
                delta = 0;
        }
@@ -2455,7 +2498,7 @@ static __always_inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer
 
 static inline void rb_event_discard(struct ring_buffer_event *event)
 {
-       if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+       if (extended_time(event))
                event = skip_time_extend(event);
 
        /* array[0] holds the actual length for the discarded event */
@@ -2499,10 +2542,11 @@ rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
                        cpu_buffer->write_stamp =
                                cpu_buffer->commit_page->page->time_stamp;
                else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
-                       delta = event->array[0];
-                       delta <<= TS_SHIFT;
-                       delta += event->time_delta;
+                       delta = ring_buffer_event_time_stamp(event);
                        cpu_buffer->write_stamp += delta;
+               } else if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
+                       delta = ring_buffer_event_time_stamp(event);
+                       cpu_buffer->write_stamp = delta;
                } else
                        cpu_buffer->write_stamp += event->time_delta;
        }
@@ -2585,22 +2629,19 @@ static __always_inline int
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
        unsigned int val = cpu_buffer->current_context;
+       unsigned long pc = preempt_count();
        int bit;
 
-       if (in_interrupt()) {
-               if (in_nmi())
-                       bit = RB_CTX_NMI;
-               else if (in_irq())
-                       bit = RB_CTX_IRQ;
-               else
-                       bit = RB_CTX_SOFTIRQ;
-       } else
+       if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
                bit = RB_CTX_NORMAL;
+       else
+               bit = pc & NMI_MASK ? RB_CTX_NMI :
+                       pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
 
-       if (unlikely(val & (1 << bit)))
+       if (unlikely(val & (1 << (bit + cpu_buffer->nest))))
                return 1;
 
-       val |= (1 << bit);
+       val |= (1 << (bit + cpu_buffer->nest));
        cpu_buffer->current_context = val;
 
        return 0;
@@ -2609,7 +2650,57 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 static __always_inline void
 trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-       cpu_buffer->current_context &= cpu_buffer->current_context - 1;
+       cpu_buffer->current_context &=
+               cpu_buffer->current_context - (1 << cpu_buffer->nest);
+}
+
+/* The recursive locking above uses 4 bits */
+#define NESTED_BITS 4
+
+/**
+ * ring_buffer_nest_start - Allow to trace while nested
+ * @buffer: The ring buffer to modify
+ *
+ * The ring buffer has a safty mechanism to prevent recursion.
+ * But there may be a case where a trace needs to be done while
+ * tracing something else. In this case, calling this function
+ * will allow this function to nest within a currently active
+ * ring_buffer_lock_reserve().
+ *
+ * Call this function before calling another ring_buffer_lock_reserve() and
+ * call ring_buffer_nest_end() after the nested ring_buffer_unlock_commit().
+ */
+void ring_buffer_nest_start(struct ring_buffer *buffer)
+{
+       struct ring_buffer_per_cpu *cpu_buffer;
+       int cpu;
+
+       /* Enabled by ring_buffer_nest_end() */
+       preempt_disable_notrace();
+       cpu = raw_smp_processor_id();
+       cpu_buffer = buffer->buffers[cpu];
+       /* This is the shift value for the above recusive locking */
+       cpu_buffer->nest += NESTED_BITS;
+}
+
+/**
+ * ring_buffer_nest_end - Allow to trace while nested
+ * @buffer: The ring buffer to modify
+ *
+ * Must be called after ring_buffer_nest_start() and after the
+ * ring_buffer_unlock_commit().
+ */
+void ring_buffer_nest_end(struct ring_buffer *buffer)
+{
+       struct ring_buffer_per_cpu *cpu_buffer;
+       int cpu;
+
+       /* disabled by ring_buffer_nest_start() */
+       cpu = raw_smp_processor_id();
+       cpu_buffer = buffer->buffers[cpu];
+       /* This is the shift value for the above recusive locking */
+       cpu_buffer->nest -= NESTED_BITS;
+       preempt_enable_notrace();
 }
 
 /**
@@ -2685,7 +2776,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
         * If this is the first commit on the page, then it has the same
         * timestamp as the page itself.
         */
-       if (!tail)
+       if (!tail && !ring_buffer_time_stamp_abs(cpu_buffer->buffer))
                info->delta = 0;
 
        /* See if we shot pass the end of this buffer page */
@@ -2762,8 +2853,11 @@ rb_reserve_next_event(struct ring_buffer *buffer,
        /* make sure this diff is calculated here */
        barrier();
 
-       /* Did the write stamp get updated already? */
-       if (likely(info.ts >= cpu_buffer->write_stamp)) {
+       if (ring_buffer_time_stamp_abs(buffer)) {
+               info.delta = info.ts;
+               rb_handle_timestamp(cpu_buffer, &info);
+       } else /* Did the write stamp get updated already? */
+               if (likely(info.ts >= cpu_buffer->write_stamp)) {
                info.delta = diff;
                if (unlikely(test_time_stamp(info.delta)))
                        rb_handle_timestamp(cpu_buffer, &info);
@@ -3461,14 +3555,13 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
                return;
 
        case RINGBUF_TYPE_TIME_EXTEND:
-               delta = event->array[0];
-               delta <<= TS_SHIFT;
-               delta += event->time_delta;
+               delta = ring_buffer_event_time_stamp(event);
                cpu_buffer->read_stamp += delta;
                return;
 
        case RINGBUF_TYPE_TIME_STAMP:
-               /* FIXME: not implemented */
+               delta = ring_buffer_event_time_stamp(event);
+               cpu_buffer->read_stamp = delta;
                return;
 
        case RINGBUF_TYPE_DATA:
@@ -3492,14 +3585,13 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
                return;
 
        case RINGBUF_TYPE_TIME_EXTEND:
-               delta = event->array[0];
-               delta <<= TS_SHIFT;
-               delta += event->time_delta;
+               delta = ring_buffer_event_time_stamp(event);
                iter->read_stamp += delta;
                return;
 
        case RINGBUF_TYPE_TIME_STAMP:
-               /* FIXME: not implemented */
+               delta = ring_buffer_event_time_stamp(event);
+               iter->read_stamp = delta;
                return;
 
        case RINGBUF_TYPE_DATA:
@@ -3723,6 +3815,8 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
        struct buffer_page *reader;
        int nr_loops = 0;
 
+       if (ts)
+               *ts = 0;
  again:
        /*
         * We repeat when a time extend is encountered.
@@ -3759,12 +3853,17 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
                goto again;
 
        case RINGBUF_TYPE_TIME_STAMP:
-               /* FIXME: not implemented */
+               if (ts) {
+                       *ts = ring_buffer_event_time_stamp(event);
+                       ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+                                                        cpu_buffer->cpu, ts);
+               }
+               /* Internal data, OK to advance */
                rb_advance_reader(cpu_buffer);
                goto again;
 
        case RINGBUF_TYPE_DATA:
-               if (ts) {
+               if (ts && !(*ts)) {
                        *ts = cpu_buffer->read_stamp + event->time_delta;
                        ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
                                                         cpu_buffer->cpu, ts);
@@ -3789,6 +3888,9 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
        struct ring_buffer_event *event;
        int nr_loops = 0;
 
+       if (ts)
+               *ts = 0;
+
        cpu_buffer = iter->cpu_buffer;
        buffer = cpu_buffer->buffer;
 
@@ -3841,12 +3943,17 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
                goto again;
 
        case RINGBUF_TYPE_TIME_STAMP:
-               /* FIXME: not implemented */
+               if (ts) {
+                       *ts = ring_buffer_event_time_stamp(event);
+                       ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
+                                                        cpu_buffer->cpu, ts);
+               }
+               /* Internal data, OK to advance */
                rb_advance_iter(iter);
                goto again;
 
        case RINGBUF_TYPE_DATA:
-               if (ts) {
+               if (ts && !(*ts)) {
                        *ts = iter->read_stamp + event->time_delta;
                        ring_buffer_normalize_time_stamp(buffer,
                                                         cpu_buffer->cpu, ts);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e9cbb96cd99e..4fc60e5ec4b9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1170,6 +1170,14 @@ static struct {
        ARCH_TRACE_CLOCKS
 };
 
+bool trace_clock_in_ns(struct trace_array *tr)
+{
+       if (trace_clocks[tr->clock_id].in_ns)
+               return true;
+
+       return false;
+}
+
 /*
  * trace_parser_get_init - gets the buffer for trace parser
  */
@@ -2127,6 +2135,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
        struct task_struct *tsk = current;
 
        entry->preempt_count            = pc & 0xff;
+       entry->preempt_lazy_count       = preempt_lazy_count();
        entry->pid                      = (tsk) ? tsk->pid : 0;
        entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
@@ -2137,8 +2146,11 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
                ((pc & NMI_MASK    ) ? TRACE_FLAG_NMI     : 0) |
                ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
                ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
-               (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
+               (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) |
+               (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) |
                (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
+
+       entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0;
 }
 EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
@@ -2275,7 +2287,7 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 
        *current_rb = trace_file->tr->trace_buffer.buffer;
 
-       if ((trace_file->flags &
+       if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags &
             (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
            (entry = this_cpu_read(trace_buffered_event))) {
                /* Try to use the per cpu buffer first */
@@ -3342,14 +3354,17 @@ get_total_entries(struct trace_buffer *buf,
 
 static void print_lat_help_header(struct seq_file *m)
 {
-       seq_puts(m, "#                  _------=> CPU#            \n"
-                   "#                 / _-----=> irqs-off        \n"
-                   "#                | / _----=> need-resched    \n"
-                   "#                || / _---=> hardirq/softirq \n"
-                   "#                ||| / _--=> preempt-depth   \n"
-                   "#                |||| /     delay            \n"
-                   "#  cmd     pid   ||||| time  |   caller      \n"
-                   "#     \\   /      |||||  \\    |   /         \n");
+       seq_puts(m, "#                  _--------=> CPU#              \n"
+                   "#                 / _-------=> irqs-off          \n"
+                   "#                | / _------=> need-resched      \n"
+                   "#                || / _-----=> need-resched_lazy \n"
+                   "#                ||| / _----=> hardirq/softirq   \n"
+                   "#                |||| / _---=> preempt-depth     \n"
+                   "#                ||||| / _--=> preempt-lazy-depth\n"
+                   "#                |||||| / _-=> migrate-disable   \n"
+                   "#                ||||||| /     delay             \n"
+                   "# cmd     pid    |||||||| time   |  caller       \n"
+                   "#     \\   /      ||||||||   \\    |  /            \n");
 }
 
 static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
@@ -3385,15 +3400,17 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
                   tgid ? tgid_space : space);
        seq_printf(m, "#                          %s / _----=> need-resched\n",
                   tgid ? tgid_space : space);
-       seq_printf(m, "#                          %s| / _---=> hardirq/softirq\n",
+       seq_printf(m, "#                          %s| /  _----=> need-resched_lazy\n",
+                  tgid ? tgid_space : space);
+       seq_printf(m, "#                          %s|| / _---=> hardirq/softirq\n",
                   tgid ? tgid_space : space);
-       seq_printf(m, "#                          %s|| / _--=> preempt-depth\n",
+       seq_printf(m, "#                          %s||| / _--=> preempt-depth\n",
                   tgid ? tgid_space : space);
-       seq_printf(m, "#                          %s||| /     delay\n",
+       seq_printf(m, "#                          %s|||| /     delay\n",
                   tgid ? tgid_space : space);
-       seq_printf(m, "#           TASK-PID %sCPU#  ||||    TIMESTAMP  FUNCTION\n",
+       seq_printf(m, "#           TASK-PID %sCPU#  |||||    TIMESTAMP  FUNCTION\n",
                   tgid ? "   TGID   " : space);
-       seq_printf(m, "#              | |   %s  |   ||||       |         |\n",
+       seq_printf(m, "#              | |   %s  |   |||||       |         |\n",
                   tgid ? "     |    " : space);
 }
 
@@ -4531,6 +4548,9 @@ static const char readme_msg[] =
 #ifdef CONFIG_X86_64
        "     x86-tsc:   TSC cycle counter\n"
 #endif
+       "\n  timestamp_mode\t-view the mode used to timestamp events\n"
+       "       delta:   Delta difference against a buffer-wide timestamp\n"
+       "    absolute:   Absolute (standalone) timestamp\n"
        "\n  trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
        "\n  trace_marker_raw\t\t- Writes into this file writes binary data into the kernel buffer\n"
        "  tracing_cpumask\t- Limit which CPUs to trace\n"
@@ -4707,8 +4727,9 @@ static const char readme_msg[] =
        "\t            .sym        display an address as a symbol\n"
        "\t            .sym-offset display an address as a symbol and offset\n"
        "\t            .execname   display a common_pid as a program name\n"
-       "\t            .syscall    display a syscall id as a syscall name\n\n"
-       "\t            .log2       display log2 value rather than raw number\n\n"
+       "\t            .syscall    display a syscall id as a syscall name\n"
+       "\t            .log2       display log2 value rather than raw number\n"
+       "\t            .usecs      display a common_timestamp in microseconds\n\n"
        "\t    The 'pause' parameter can be used to pause an existing hist\n"
        "\t    trigger or to start a hist trigger but not log any events\n"
        "\t    until told to do so.  'continue' can be used to start or\n"
@@ -6218,7 +6239,7 @@ static int tracing_clock_show(struct seq_file *m, void *v)
        return 0;
 }
 
-static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
+int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 {
        int i;
 
@@ -6298,6 +6319,71 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
        return ret;
 }
 
+static int tracing_time_stamp_mode_show(struct seq_file *m, void *v)
+{
+       struct trace_array *tr = m->private;
+
+       mutex_lock(&trace_types_lock);
+
+       if (ring_buffer_time_stamp_abs(tr->trace_buffer.buffer))
+               seq_puts(m, "delta [absolute]\n");
+       else
+               seq_puts(m, "[delta] absolute\n");
+
+       mutex_unlock(&trace_types_lock);
+
+       return 0;
+}
+
+static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
+{
+       struct trace_array *tr = inode->i_private;
+       int ret;
+
+       if (tracing_disabled)
+               return -ENODEV;
+
+       if (trace_array_get(tr))
+               return -ENODEV;
+
+       ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private);
+       if (ret < 0)
+               trace_array_put(tr);
+
+       return ret;
+}
+
+int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs)
+{
+       int ret = 0;
+
+       mutex_lock(&trace_types_lock);
+
+       if (abs && tr->time_stamp_abs_ref++)
+               goto out;
+
+       if (!abs) {
+               if (WARN_ON_ONCE(!tr->time_stamp_abs_ref)) {
+                       ret = -EINVAL;
+                       goto out;
+               }
+
+               if (--tr->time_stamp_abs_ref)
+                       goto out;
+       }
+
+       ring_buffer_set_time_stamp_abs(tr->trace_buffer.buffer, abs);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+       if (tr->max_buffer.buffer)
+               ring_buffer_set_time_stamp_abs(tr->max_buffer.buffer, abs);
+#endif
+ out:
+       mutex_unlock(&trace_types_lock);
+
+       return ret;
+}
+
 struct ftrace_buffer_info {
        struct trace_iterator   iter;
        void                    *spare;
@@ -6545,6 +6631,13 @@ static const struct file_operations trace_clock_fops = {
        .write          = tracing_clock_write,
 };
 
+static const struct file_operations trace_time_stamp_mode_fops = {
+       .open           = tracing_time_stamp_mode_open,
+       .read           = seq_read,
+       .llseek         = seq_lseek,
+       .release        = tracing_single_release_tr,
+};
+
 #ifdef CONFIG_TRACER_SNAPSHOT
 static const struct file_operations snapshot_fops = {
        .open           = tracing_snapshot_open,
@@ -7684,6 +7777,7 @@ static int instance_mkdir(const char *name)
        struct trace_array *tr;
        int ret;
 
+       mutex_lock(&event_mutex);
        mutex_lock(&trace_types_lock);
 
        ret = -EEXIST;
@@ -7716,6 +7810,7 @@ static int instance_mkdir(const char *name)
 
        INIT_LIST_HEAD(&tr->systems);
        INIT_LIST_HEAD(&tr->events);
+       INIT_LIST_HEAD(&tr->hist_vars);
 
        if (allocate_trace_buffers(tr, trace_buf_size) < 0)
                goto out_free_tr;
@@ -7739,6 +7834,7 @@ static int instance_mkdir(const char *name)
        list_add(&tr->list, &ftrace_trace_arrays);
 
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
 
        return 0;
 
@@ -7750,6 +7846,7 @@ static int instance_mkdir(const char *name)
 
  out_unlock:
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
 
        return ret;
 
@@ -7762,6 +7859,7 @@ static int instance_rmdir(const char *name)
        int ret;
        int i;
 
+       mutex_lock(&event_mutex);
        mutex_lock(&trace_types_lock);
 
        ret = -ENODEV;
@@ -7807,6 +7905,7 @@ static int instance_rmdir(const char *name)
 
  out_unlock:
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
 
        return ret;
 }
@@ -7864,6 +7963,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
        trace_create_file("tracing_on", 0644, d_tracer,
                          tr, &rb_simple_fops);
 
+       trace_create_file("timestamp_mode", 0444, d_tracer, tr,
+                         &trace_time_stamp_mode_fops);
+
        create_trace_options_dir(tr);
 
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
@@ -8275,6 +8377,92 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 }
 EXPORT_SYMBOL_GPL(ftrace_dump);
 
+int trace_run_command(const char *buf, int (*createfn)(int, char **))
+{
+       char **argv;
+       int argc, ret;
+
+       argc = 0;
+       ret = 0;
+       argv = argv_split(GFP_KERNEL, buf, &argc);
+       if (!argv)
+               return -ENOMEM;
+
+       if (argc)
+               ret = createfn(argc, argv);
+
+       argv_free(argv);
+
+       return ret;
+}
+
+#define WRITE_BUFSIZE  4096
+
+ssize_t trace_parse_run_command(struct file *file, const char __user *buffer,
+                               size_t count, loff_t *ppos,
+                               int (*createfn)(int, char **))
+{
+       char *kbuf, *buf, *tmp;
+       int ret = 0;
+       size_t done = 0;
+       size_t size;
+
+       kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+       if (!kbuf)
+               return -ENOMEM;
+
+       while (done < count) {
+               size = count - done;
+
+               if (size >= WRITE_BUFSIZE)
+                       size = WRITE_BUFSIZE - 1;
+
+               if (copy_from_user(kbuf, buffer + done, size)) {
+                       ret = -EFAULT;
+                       goto out;
+               }
+               kbuf[size] = '\0';
+               buf = kbuf;
+               do {
+                       tmp = strchr(buf, '\n');
+                       if (tmp) {
+                               *tmp = '\0';
+                               size = tmp - buf + 1;
+                       } else {
+                               size = strlen(buf);
+                               if (done + size < count) {
+                                       if (buf != kbuf)
+                                               break;
+                                       /* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */
+                                       pr_warn("Line length is too long: Should be less than %d\n",
+                                               WRITE_BUFSIZE - 2);
+                                       ret = -EINVAL;
+                                       goto out;
+                               }
+                       }
+                       done += size;
+
+                       /* Remove comments */
+                       tmp = strchr(buf, '#');
+
+                       if (tmp)
+                               *tmp = '\0';
+
+                       ret = trace_run_command(buf, createfn);
+                       if (ret)
+                               goto out;
+                       buf += size;
+
+               } while (done < count);
+       }
+       ret = done;
+
+out:
+       kfree(kbuf);
+
+       return ret;
+}
+
 __init static int tracer_alloc_buffers(void)
 {
        int ring_buf_size;
@@ -8375,6 +8563,7 @@ __init static int tracer_alloc_buffers(void)
 
        INIT_LIST_HEAD(&global_trace.systems);
        INIT_LIST_HEAD(&global_trace.events);
+       INIT_LIST_HEAD(&global_trace.hist_vars);
        list_add(&global_trace.list, &ftrace_trace_arrays);
 
        apply_trace_boot_options();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 851cd1605085..18bf383f46e8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -127,6 +127,7 @@ struct kretprobe_trace_entry_head {
  *  NEED_RESCHED       - reschedule is requested
  *  HARDIRQ            - inside an interrupt handler
  *  SOFTIRQ            - inside a softirq handler
+ *  NEED_RESCHED_LAZY  - lazy reschedule is requested
  */
 enum trace_flag_type {
        TRACE_FLAG_IRQS_OFF             = 0x01,
@@ -136,6 +137,7 @@ enum trace_flag_type {
        TRACE_FLAG_SOFTIRQ              = 0x10,
        TRACE_FLAG_PREEMPT_RESCHED      = 0x20,
        TRACE_FLAG_NMI                  = 0x40,
+       TRACE_FLAG_NEED_RESCHED_LAZY    = 0x80,
 };
 
 #define TRACE_BUF_SIZE         1024
@@ -273,6 +275,8 @@ struct trace_array {
        /* function tracing enabled */
        int                     function_enabled;
 #endif
+       int                     time_stamp_abs_ref;
+       struct list_head        hist_vars;
 };
 
 enum {
@@ -286,6 +290,11 @@ extern struct mutex trace_types_lock;
 extern int trace_array_get(struct trace_array *tr);
 extern void trace_array_put(struct trace_array *tr);
 
+extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
+extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
+
+extern bool trace_clock_in_ns(struct trace_array *tr);
+
 /*
  * The global tracer (top) should be the first trace array added,
  * but we check the flag anyway.
@@ -1293,7 +1302,7 @@ __event_trigger_test_discard(struct trace_event_file *file,
        unsigned long eflags = file->flags;
 
        if (eflags & EVENT_FILE_FL_TRIGGER_COND)
-               *tt = event_triggers_call(file, entry);
+               *tt = event_triggers_call(file, entry, event);
 
        if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
            (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
@@ -1330,7 +1339,7 @@ event_trigger_unlock_commit(struct trace_event_file *file,
                trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc);
 
        if (tt)
-               event_triggers_post_call(file, tt, entry);
+               event_triggers_post_call(file, tt, entry, event);
 }
 
 /**
@@ -1363,7 +1372,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file,
                                                irq_flags, pc, regs);
 
        if (tt)
-               event_triggers_post_call(file, tt, entry);
+               event_triggers_post_call(file, tt, entry, event);
 }
 
 #define FILTER_PRED_INVALID    ((unsigned short)-1)
@@ -1545,6 +1554,8 @@ extern void pause_named_trigger(struct event_trigger_data *data);
 extern void unpause_named_trigger(struct event_trigger_data *data);
 extern void set_named_trigger_data(struct event_trigger_data *data,
                                   struct event_trigger_data *named_data);
+extern struct event_trigger_data *
+get_named_trigger_data(struct event_trigger_data *data);
 extern int register_event_command(struct event_command *cmd);
 extern int unregister_event_command(struct event_command *cmd);
 extern int register_trigger_hist_enable_disable_cmds(void);
@@ -1588,7 +1599,8 @@ extern int register_trigger_hist_enable_disable_cmds(void);
  */
 struct event_trigger_ops {
        void                    (*func)(struct event_trigger_data *data,
-                                       void *rec);
+                                       void *rec,
+                                       struct ring_buffer_event *rbe);
        int                     (*init)(struct event_trigger_ops *ops,
                                        struct event_trigger_data *data);
        void                    (*free)(struct event_trigger_ops *ops,
@@ -1755,6 +1767,13 @@ void trace_printk_start_comm(void);
 int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
 int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
 
+#define MAX_EVENT_NAME_LEN     64
+
+extern int trace_run_command(const char *buf, int (*createfn)(int, char**));
+extern ssize_t trace_parse_run_command(struct file *file,
+               const char __user *buffer, size_t count, loff_t *ppos,
+               int (*createfn)(int, char**));
+
 /*
  * Normal trace_printk() and friends allocates special buffers
  * to do the manipulation, as well as saves the print formats
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d53268a4e167..9ba230a4052f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -187,6 +187,8 @@ static int trace_define_common_fields(void)
        __common_field(unsigned char, flags);
        __common_field(unsigned char, preempt_count);
        __common_field(int, pid);
+       __common_field(unsigned short, migrate_disable);
+       __common_field(unsigned short, padding);
 
        return ret;
 }
@@ -1406,8 +1408,8 @@ static int subsystem_open(struct inode *inode, struct file *filp)
                return -ENODEV;
 
        /* Make sure the system still exists */
-       mutex_lock(&trace_types_lock);
        mutex_lock(&event_mutex);
+       mutex_lock(&trace_types_lock);
        list_for_each_entry(tr, &ftrace_trace_arrays, list) {
                list_for_each_entry(dir, &tr->systems, list) {
                        if (dir == inode->i_private) {
@@ -1421,8 +1423,8 @@ static int subsystem_open(struct inode *inode, struct file *filp)
                }
        }
  exit_loop:
-       mutex_unlock(&event_mutex);
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
 
        if (!system)
                return -ENODEV;
@@ -2308,15 +2310,15 @@ static void __add_event_to_tracers(struct trace_event_call *call);
 int trace_add_event_call(struct trace_event_call *call)
 {
        int ret;
-       mutex_lock(&trace_types_lock);
        mutex_lock(&event_mutex);
+       mutex_lock(&trace_types_lock);
 
        ret = __register_event(call, NULL);
        if (ret >= 0)
                __add_event_to_tracers(call);
 
-       mutex_unlock(&event_mutex);
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
        return ret;
 }
 
@@ -2370,13 +2372,13 @@ int trace_remove_event_call(struct trace_event_call *call)
 {
        int ret;
 
-       mutex_lock(&trace_types_lock);
        mutex_lock(&event_mutex);
+       mutex_lock(&trace_types_lock);
        down_write(&trace_event_sem);
        ret = probe_remove_event_call(call);
        up_write(&trace_event_sem);
-       mutex_unlock(&event_mutex);
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
 
        return ret;
 }
@@ -2438,8 +2440,8 @@ static int trace_module_notify(struct notifier_block *self,
 {
        struct module *mod = data;
 
-       mutex_lock(&trace_types_lock);
        mutex_lock(&event_mutex);
+       mutex_lock(&trace_types_lock);
        switch (val) {
        case MODULE_STATE_COMING:
                trace_module_add_events(mod);
@@ -2448,8 +2450,8 @@ static int trace_module_notify(struct notifier_block *self,
                trace_module_remove_events(mod);
                break;
        }
-       mutex_unlock(&event_mutex);
        mutex_unlock(&trace_types_lock);
+       mutex_unlock(&event_mutex);
 
        return 0;
 }
@@ -2964,24 +2966,24 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
  * creates the event hierachry in the @parent/events directory.
  *
  * Returns 0 on success.
+ *
+ * Must be called with event_mutex held.
  */
 int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
 {
        int ret;
 
-       mutex_lock(&event_mutex);
+       lockdep_assert_held(&event_mutex);
 
        ret = create_event_toplevel_files(parent, tr);
        if (ret)
-               goto out_unlock;
+               goto out;
 
        down_write(&trace_event_sem);
        __trace_add_event_dirs(tr);
        up_write(&trace_event_sem);
 
- out_unlock:
-       mutex_unlock(&event_mutex);
-
+ out:
        return ret;
 }
 
@@ -3010,9 +3012,10 @@ early_event_add_tracer(struct dentry *parent, struct trace_array *tr)
        return ret;
 }
 
+/* Must be called with event_mutex held */
 int event_trace_del_tracer(struct trace_array *tr)
 {
-       mutex_lock(&event_mutex);
+       lockdep_assert_held(&event_mutex);
 
        /* Disable any event triggers and associated soft-disabled events */
        clear_event_triggers(tr);
@@ -3033,8 +3036,6 @@ int event_trace_del_tracer(struct trace_array *tr)
 
        tr->event_dir = NULL;
 
-       mutex_unlock(&event_mutex);
-
        return 0;
 }
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 7eb975a2d0e1..24bc0769fdd6 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -20,13 +20,39 @@
 #include <linux/slab.h>
 #include <linux/stacktrace.h>
 #include <linux/rculist.h>
+#include <linux/tracefs.h>
 
 #include "tracing_map.h"
 #include "trace.h"
 
+#define SYNTH_SYSTEM           "synthetic"
+#define SYNTH_FIELDS_MAX       16
+
+#define STR_VAR_LEN_MAX                32 /* must be multiple of sizeof(u64) */
+
 struct hist_field;
 
-typedef u64 (*hist_field_fn_t) (struct hist_field *field, void *event);
+typedef u64 (*hist_field_fn_t) (struct hist_field *field,
+                               struct tracing_map_elt *elt,
+                               struct ring_buffer_event *rbe,
+                               void *event);
+
+#define HIST_FIELD_OPERANDS_MAX        2
+#define HIST_FIELDS_MAX                (TRACING_MAP_FIELDS_MAX + TRACING_MAP_VARS_MAX)
+#define HIST_ACTIONS_MAX       8
+
+enum field_op_id {
+       FIELD_OP_NONE,
+       FIELD_OP_PLUS,
+       FIELD_OP_MINUS,
+       FIELD_OP_UNARY_MINUS,
+};
+
+struct hist_var {
+       char                            *name;
+       struct hist_trigger_data        *hist_data;
+       unsigned int                    idx;
+};
 
 struct hist_field {
        struct ftrace_event_field       *field;
@@ -34,26 +60,50 @@ struct hist_field {
        hist_field_fn_t                 fn;
        unsigned int                    size;
        unsigned int                    offset;
+       unsigned int                    is_signed;
+       const char                      *type;
+       struct hist_field               *operands[HIST_FIELD_OPERANDS_MAX];
+       struct hist_trigger_data        *hist_data;
+       struct hist_var                 var;
+       enum field_op_id                operator;
+       char                            *system;
+       char                            *event_name;
+       char                            *name;
+       unsigned int                    var_idx;
+       unsigned int                    var_ref_idx;
+       bool                            read_once;
 };
 
-static u64 hist_field_none(struct hist_field *field, void *event)
+static u64 hist_field_none(struct hist_field *field,
+                          struct tracing_map_elt *elt,
+                          struct ring_buffer_event *rbe,
+                          void *event)
 {
        return 0;
 }
 
-static u64 hist_field_counter(struct hist_field *field, void *event)
+static u64 hist_field_counter(struct hist_field *field,
+                             struct tracing_map_elt *elt,
+                             struct ring_buffer_event *rbe,
+                             void *event)
 {
        return 1;
 }
 
-static u64 hist_field_string(struct hist_field *hist_field, void *event)
+static u64 hist_field_string(struct hist_field *hist_field,
+                            struct tracing_map_elt *elt,
+                            struct ring_buffer_event *rbe,
+                            void *event)
 {
        char *addr = (char *)(event + hist_field->field->offset);
 
        return (u64)(unsigned long)addr;
 }
 
-static u64 hist_field_dynstring(struct hist_field *hist_field, void *event)
+static u64 hist_field_dynstring(struct hist_field *hist_field,
+                               struct tracing_map_elt *elt,
+                               struct ring_buffer_event *rbe,
+                               void *event)
 {
        u32 str_item = *(u32 *)(event + hist_field->field->offset);
        int str_loc = str_item & 0xffff;
@@ -62,22 +112,74 @@ static u64 hist_field_dynstring(struct hist_field *hist_field, void *event)
        return (u64)(unsigned long)addr;
 }
 
-static u64 hist_field_pstring(struct hist_field *hist_field, void *event)
+static u64 hist_field_pstring(struct hist_field *hist_field,
+                             struct tracing_map_elt *elt,
+                             struct ring_buffer_event *rbe,
+                             void *event)
 {
        char **addr = (char **)(event + hist_field->field->offset);
 
        return (u64)(unsigned long)*addr;
 }
 
-static u64 hist_field_log2(struct hist_field *hist_field, void *event)
+static u64 hist_field_log2(struct hist_field *hist_field,
+                          struct tracing_map_elt *elt,
+                          struct ring_buffer_event *rbe,
+                          void *event)
 {
-       u64 val = *(u64 *)(event + hist_field->field->offset);
+       struct hist_field *operand = hist_field->operands[0];
+
+       u64 val = operand->fn(operand, elt, rbe, event);
 
        return (u64) ilog2(roundup_pow_of_two(val));
 }
 
+static u64 hist_field_plus(struct hist_field *hist_field,
+                          struct tracing_map_elt *elt,
+                          struct ring_buffer_event *rbe,
+                          void *event)
+{
+       struct hist_field *operand1 = hist_field->operands[0];
+       struct hist_field *operand2 = hist_field->operands[1];
+
+       u64 val1 = operand1->fn(operand1, elt, rbe, event);
+       u64 val2 = operand2->fn(operand2, elt, rbe, event);
+
+       return val1 + val2;
+}
+
+static u64 hist_field_minus(struct hist_field *hist_field,
+                           struct tracing_map_elt *elt,
+                           struct ring_buffer_event *rbe,
+                           void *event)
+{
+       struct hist_field *operand1 = hist_field->operands[0];
+       struct hist_field *operand2 = hist_field->operands[1];
+
+       u64 val1 = operand1->fn(operand1, elt, rbe, event);
+       u64 val2 = operand2->fn(operand2, elt, rbe, event);
+
+       return val1 - val2;
+}
+
+static u64 hist_field_unary_minus(struct hist_field *hist_field,
+                                 struct tracing_map_elt *elt,
+                                 struct ring_buffer_event *rbe,
+                                 void *event)
+{
+       struct hist_field *operand = hist_field->operands[0];
+
+       s64 sval = (s64)operand->fn(operand, elt, rbe, event);
+       u64 val = (u64)-sval;
+
+       return val;
+}
+
 #define DEFINE_HIST_FIELD_FN(type)                                     \
-static u64 hist_field_##type(struct hist_field *hist_field, void *event)\
+       static u64 hist_field_##type(struct hist_field *hist_field,     \
+                                    struct tracing_map_elt *elt,       \
+                                    struct ring_buffer_event *rbe,     \
+                                    void *event)                       \
 {                                                                      \
        type *addr = (type *)(event + hist_field->field->offset);       \
                                                                        \
@@ -110,16 +212,29 @@ DEFINE_HIST_FIELD_FN(u8);
 #define HIST_KEY_SIZE_MAX      (MAX_FILTER_STR_VAL + HIST_STACKTRACE_SIZE)
 
 enum hist_field_flags {
-       HIST_FIELD_FL_HITCOUNT          = 1,
-       HIST_FIELD_FL_KEY               = 2,
-       HIST_FIELD_FL_STRING            = 4,
-       HIST_FIELD_FL_HEX               = 8,
-       HIST_FIELD_FL_SYM               = 16,
-       HIST_FIELD_FL_SYM_OFFSET        = 32,
-       HIST_FIELD_FL_EXECNAME          = 64,
-       HIST_FIELD_FL_SYSCALL           = 128,
-       HIST_FIELD_FL_STACKTRACE        = 256,
-       HIST_FIELD_FL_LOG2              = 512,
+       HIST_FIELD_FL_HITCOUNT          = 1 << 0,
+       HIST_FIELD_FL_KEY               = 1 << 1,
+       HIST_FIELD_FL_STRING            = 1 << 2,
+       HIST_FIELD_FL_HEX               = 1 << 3,
+       HIST_FIELD_FL_SYM               = 1 << 4,
+       HIST_FIELD_FL_SYM_OFFSET        = 1 << 5,
+       HIST_FIELD_FL_EXECNAME          = 1 << 6,
+       HIST_FIELD_FL_SYSCALL           = 1 << 7,
+       HIST_FIELD_FL_STACKTRACE        = 1 << 8,
+       HIST_FIELD_FL_LOG2              = 1 << 9,
+       HIST_FIELD_FL_TIMESTAMP         = 1 << 10,
+       HIST_FIELD_FL_TIMESTAMP_USECS   = 1 << 11,
+       HIST_FIELD_FL_VAR               = 1 << 12,
+       HIST_FIELD_FL_EXPR              = 1 << 13,
+       HIST_FIELD_FL_VAR_REF           = 1 << 14,
+       HIST_FIELD_FL_CPU               = 1 << 15,
+       HIST_FIELD_FL_ALIAS             = 1 << 16,
+};
+
+struct var_defs {
+       unsigned int    n_vars;
+       char            *name[TRACING_MAP_VARS_MAX];
+       char            *expr[TRACING_MAP_VARS_MAX];
 };
 
 struct hist_trigger_attrs {
@@ -127,298 +242,3585 @@ struct hist_trigger_attrs {
        char            *vals_str;
        char            *sort_key_str;
        char            *name;
+       char            *clock;
        bool            pause;
        bool            cont;
        bool            clear;
+       bool            ts_in_usecs;
        unsigned int    map_bits;
+
+       char            *assignment_str[TRACING_MAP_VARS_MAX];
+       unsigned int    n_assignments;
+
+       char            *action_str[HIST_ACTIONS_MAX];
+       unsigned int    n_actions;
+
+       struct var_defs var_defs;
+};
+
+struct field_var {
+       struct hist_field       *var;
+       struct hist_field       *val;
+};
+
+struct field_var_hist {
+       struct hist_trigger_data        *hist_data;
+       char                            *cmd;
 };
 
 struct hist_trigger_data {
-       struct hist_field               *fields[TRACING_MAP_FIELDS_MAX];
+       struct hist_field               *fields[HIST_FIELDS_MAX];
        unsigned int                    n_vals;
        unsigned int                    n_keys;
        unsigned int                    n_fields;
+       unsigned int                    n_vars;
        unsigned int                    key_size;
        struct tracing_map_sort_key     sort_keys[TRACING_MAP_SORT_KEYS_MAX];
        unsigned int                    n_sort_keys;
        struct trace_event_file         *event_file;
        struct hist_trigger_attrs       *attrs;
        struct tracing_map              *map;
+       bool                            enable_timestamps;
+       bool                            remove;
+       struct hist_field               *var_refs[TRACING_MAP_VARS_MAX];
+       unsigned int                    n_var_refs;
+
+       struct action_data              *actions[HIST_ACTIONS_MAX];
+       unsigned int                    n_actions;
+
+       struct hist_field               *synth_var_refs[SYNTH_FIELDS_MAX];
+       unsigned int                    n_synth_var_refs;
+       struct field_var                *field_vars[SYNTH_FIELDS_MAX];
+       unsigned int                    n_field_vars;
+       unsigned int                    n_field_var_str;
+       struct field_var_hist           *field_var_hists[SYNTH_FIELDS_MAX];
+       unsigned int                    n_field_var_hists;
+
+       struct field_var                *max_vars[SYNTH_FIELDS_MAX];
+       unsigned int                    n_max_vars;
+       unsigned int                    n_max_var_str;
 };
 
-static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
-{
-       hist_field_fn_t fn = NULL;
+struct synth_field {
+       char *type;
+       char *name;
+       size_t size;
+       bool is_signed;
+       bool is_string;
+};
 
-       switch (field_size) {
-       case 8:
-               if (field_is_signed)
-                       fn = hist_field_s64;
-               else
-                       fn = hist_field_u64;
-               break;
-       case 4:
-               if (field_is_signed)
-                       fn = hist_field_s32;
-               else
-                       fn = hist_field_u32;
-               break;
-       case 2:
-               if (field_is_signed)
-                       fn = hist_field_s16;
-               else
-                       fn = hist_field_u16;
-               break;
-       case 1:
-               if (field_is_signed)
-                       fn = hist_field_s8;
-               else
-                       fn = hist_field_u8;
-               break;
-       }
+struct synth_event {
+       struct list_head                        list;
+       int                                     ref;
+       char                                    *name;
+       struct synth_field                      **fields;
+       unsigned int                            n_fields;
+       unsigned int                            n_u64;
+       struct trace_event_class                class;
+       struct trace_event_call                 call;
+       struct tracepoint                       *tp;
+};
 
-       return fn;
+struct action_data;
+
+typedef void (*action_fn_t) (struct hist_trigger_data *hist_data,
+                            struct tracing_map_elt *elt, void *rec,
+                            struct ring_buffer_event *rbe,
+                            struct action_data *data, u64 *var_ref_vals);
+
+struct action_data {
+       action_fn_t             fn;
+       unsigned int            n_params;
+       char                    *params[SYNTH_FIELDS_MAX];
+
+       union {
+               struct {
+                       unsigned int            var_ref_idx;
+                       char                    *match_event;
+                       char                    *match_event_system;
+                       char                    *synth_event_name;
+                       struct synth_event      *synth_event;
+               } onmatch;
+
+               struct {
+                       char                    *var_str;
+                       char                    *fn_name;
+                       unsigned int            max_var_ref_idx;
+                       struct hist_field       *max_var;
+                       struct hist_field       *var;
+               } onmax;
+       };
+};
+
+
+static char last_hist_cmd[MAX_FILTER_STR_VAL];
+static char hist_err_str[MAX_FILTER_STR_VAL];
+
+static void last_cmd_set(char *str)
+{
+       if (!str)
+               return;
+
+       strncpy(last_hist_cmd, str, MAX_FILTER_STR_VAL - 1);
 }
 
-static int parse_map_size(char *str)
+static void hist_err(char *str, char *var)
 {
-       unsigned long size, map_bits;
-       int ret;
+       int maxlen = MAX_FILTER_STR_VAL - 1;
 
-       strsep(&str, "=");
-       if (!str) {
-               ret = -EINVAL;
-               goto out;
-       }
+       if (!str)
+               return;
 
-       ret = kstrtoul(str, 0, &size);
-       if (ret)
-               goto out;
+       if (strlen(hist_err_str))
+               return;
 
-       map_bits = ilog2(roundup_pow_of_two(size));
-       if (map_bits < TRACING_MAP_BITS_MIN ||
-           map_bits > TRACING_MAP_BITS_MAX)
-               ret = -EINVAL;
-       else
-               ret = map_bits;
- out:
-       return ret;
+       if (!var)
+               var = "";
+
+       if (strlen(hist_err_str) + strlen(str) + strlen(var) > maxlen)
+               return;
+
+       strcat(hist_err_str, str);
+       strcat(hist_err_str, var);
 }
 
-static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
+static void hist_err_event(char *str, char *system, char *event, char *var)
 {
-       if (!attrs)
-               return;
+       char err[MAX_FILTER_STR_VAL];
 
-       kfree(attrs->name);
-       kfree(attrs->sort_key_str);
-       kfree(attrs->keys_str);
-       kfree(attrs->vals_str);
-       kfree(attrs);
+       if (system && var)
+               snprintf(err, MAX_FILTER_STR_VAL, "%s.%s.%s", system, event, var);
+       else if (system)
+               snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
+       else
+               strncpy(err, var, MAX_FILTER_STR_VAL);
+
+       hist_err(str, err);
 }
 
-static struct hist_trigger_attrs *parse_hist_trigger_attrs(char *trigger_str)
+static void hist_err_clear(void)
 {
-       struct hist_trigger_attrs *attrs;
-       int ret = 0;
+       hist_err_str[0] = '\0';
+}
 
-       attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
-       if (!attrs)
-               return ERR_PTR(-ENOMEM);
+static bool have_hist_err(void)
+{
+       if (strlen(hist_err_str))
+               return true;
 
-       while (trigger_str) {
-               char *str = strsep(&trigger_str, ":");
+       return false;
+}
 
-               if ((strncmp(str, "key=", strlen("key=")) == 0) ||
-                   (strncmp(str, "keys=", strlen("keys=")) == 0))
-                       attrs->keys_str = kstrdup(str, GFP_KERNEL);
-               else if ((strncmp(str, "val=", strlen("val=")) == 0) ||
-                        (strncmp(str, "vals=", strlen("vals=")) == 0) ||
-                        (strncmp(str, "values=", strlen("values=")) == 0))
-                       attrs->vals_str = kstrdup(str, GFP_KERNEL);
-               else if (strncmp(str, "sort=", strlen("sort=")) == 0)
-                       attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
-               else if (strncmp(str, "name=", strlen("name=")) == 0)
-                       attrs->name = kstrdup(str, GFP_KERNEL);
-               else if (strcmp(str, "pause") == 0)
-                       attrs->pause = true;
-               else if ((strcmp(str, "cont") == 0) ||
-                        (strcmp(str, "continue") == 0))
-                       attrs->cont = true;
-               else if (strcmp(str, "clear") == 0)
-                       attrs->clear = true;
-               else if (strncmp(str, "size=", strlen("size=")) == 0) {
-                       int map_bits = parse_map_size(str);
+static LIST_HEAD(synth_event_list);
+static DEFINE_MUTEX(synth_event_mutex);
 
-                       if (map_bits < 0) {
-                               ret = map_bits;
-                               goto free;
-                       }
-                       attrs->map_bits = map_bits;
+struct synth_trace_event {
+       struct trace_entry      ent;
+       u64                     fields[];
+};
+
+static int synth_event_define_fields(struct trace_event_call *call)
+{
+       struct synth_trace_event trace;
+       int offset = offsetof(typeof(trace), fields);
+       struct synth_event *event = call->data;
+       unsigned int i, size, n_u64;
+       char *name, *type;
+       bool is_signed;
+       int ret = 0;
+
+       for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+               size = event->fields[i]->size;
+               is_signed = event->fields[i]->is_signed;
+               type = event->fields[i]->type;
+               name = event->fields[i]->name;
+               ret = trace_define_field(call, type, name, offset, size,
+                                        is_signed, FILTER_OTHER);
+               if (ret)
+                       break;
+
+               if (event->fields[i]->is_string) {
+                       offset += STR_VAR_LEN_MAX;
+                       n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
                } else {
-                       ret = -EINVAL;
-                       goto free;
+                       offset += sizeof(u64);
+                       n_u64++;
                }
        }
 
-       if (!attrs->keys_str) {
-               ret = -EINVAL;
-               goto free;
-       }
+       event->n_u64 = n_u64;
 
-       return attrs;
- free:
-       destroy_hist_trigger_attrs(attrs);
+       return ret;
+}
 
-       return ERR_PTR(ret);
+static bool synth_field_signed(char *type)
+{
+       if (strncmp(type, "u", 1) == 0)
+               return false;
+
+       return true;
 }
 
-static inline void save_comm(char *comm, struct task_struct *task)
+static int synth_field_is_string(char *type)
 {
-       if (!task->pid) {
-               strcpy(comm, "<idle>");
-               return;
-       }
+       if (strstr(type, "char[") != NULL)
+               return true;
 
-       if (WARN_ON_ONCE(task->pid < 0)) {
-               strcpy(comm, "<XXX>");
-               return;
-       }
+       return false;
+}
 
-       memcpy(comm, task->comm, TASK_COMM_LEN);
+static int synth_field_string_size(char *type)
+{
+       char buf[4], *end, *start;
+       unsigned int len;
+       int size, err;
+
+       start = strstr(type, "char[");
+       if (start == NULL)
+               return -EINVAL;
+       start += strlen("char[");
+
+       end = strchr(type, ']');
+       if (!end || end < start)
+               return -EINVAL;
+
+       len = end - start;
+       if (len > 3)
+               return -EINVAL;
+
+       strncpy(buf, start, len);
+       buf[len] = '\0';
+
+       err = kstrtouint(buf, 0, &size);
+       if (err)
+               return err;
+
+       if (size > STR_VAR_LEN_MAX)
+               return -EINVAL;
+
+       return size;
 }
 
-static void hist_trigger_elt_comm_free(struct tracing_map_elt *elt)
+static int synth_field_size(char *type)
 {
-       kfree((char *)elt->private_data);
+       int size = 0;
+
+       if (strcmp(type, "s64") == 0)
+               size = sizeof(s64);
+       else if (strcmp(type, "u64") == 0)
+               size = sizeof(u64);
+       else if (strcmp(type, "s32") == 0)
+               size = sizeof(s32);
+       else if (strcmp(type, "u32") == 0)
+               size = sizeof(u32);
+       else if (strcmp(type, "s16") == 0)
+               size = sizeof(s16);
+       else if (strcmp(type, "u16") == 0)
+               size = sizeof(u16);
+       else if (strcmp(type, "s8") == 0)
+               size = sizeof(s8);
+       else if (strcmp(type, "u8") == 0)
+               size = sizeof(u8);
+       else if (strcmp(type, "char") == 0)
+               size = sizeof(char);
+       else if (strcmp(type, "unsigned char") == 0)
+               size = sizeof(unsigned char);
+       else if (strcmp(type, "int") == 0)
+               size = sizeof(int);
+       else if (strcmp(type, "unsigned int") == 0)
+               size = sizeof(unsigned int);
+       else if (strcmp(type, "long") == 0)
+               size = sizeof(long);
+       else if (strcmp(type, "unsigned long") == 0)
+               size = sizeof(unsigned long);
+       else if (strcmp(type, "pid_t") == 0)
+               size = sizeof(pid_t);
+       else if (synth_field_is_string(type))
+               size = synth_field_string_size(type);
+
+       return size;
 }
 
-static int hist_trigger_elt_comm_alloc(struct tracing_map_elt *elt)
+static const char *synth_field_fmt(char *type)
 {
-       struct hist_trigger_data *hist_data = elt->map->private_data;
-       struct hist_field *key_field;
-       unsigned int i;
+       const char *fmt = "%llu";
+
+       if (strcmp(type, "s64") == 0)
+               fmt = "%lld";
+       else if (strcmp(type, "u64") == 0)
+               fmt = "%llu";
+       else if (strcmp(type, "s32") == 0)
+               fmt = "%d";
+       else if (strcmp(type, "u32") == 0)
+               fmt = "%u";
+       else if (strcmp(type, "s16") == 0)
+               fmt = "%d";
+       else if (strcmp(type, "u16") == 0)
+               fmt = "%u";
+       else if (strcmp(type, "s8") == 0)
+               fmt = "%d";
+       else if (strcmp(type, "u8") == 0)
+               fmt = "%u";
+       else if (strcmp(type, "char") == 0)
+               fmt = "%d";
+       else if (strcmp(type, "unsigned char") == 0)
+               fmt = "%u";
+       else if (strcmp(type, "int") == 0)
+               fmt = "%d";
+       else if (strcmp(type, "unsigned int") == 0)
+               fmt = "%u";
+       else if (strcmp(type, "long") == 0)
+               fmt = "%ld";
+       else if (strcmp(type, "unsigned long") == 0)
+               fmt = "%lu";
+       else if (strcmp(type, "pid_t") == 0)
+               fmt = "%d";
+       else if (synth_field_is_string(type))
+               fmt = "%s";
+
+       return fmt;
+}
 
-       for_each_hist_key_field(i, hist_data) {
-               key_field = hist_data->fields[i];
+static enum print_line_t print_synth_event(struct trace_iterator *iter,
+                                          int flags,
+                                          struct trace_event *event)
+{
+       struct trace_array *tr = iter->tr;
+       struct trace_seq *s = &iter->seq;
+       struct synth_trace_event *entry;
+       struct synth_event *se;
+       unsigned int i, n_u64;
+       char print_fmt[32];
+       const char *fmt;
 
-               if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
-                       unsigned int size = TASK_COMM_LEN + 1;
+       entry = (struct synth_trace_event *)iter->ent;
+       se = container_of(event, struct synth_event, call.event);
 
-                       elt->private_data = kzalloc(size, GFP_KERNEL);
-                       if (!elt->private_data)
-                               return -ENOMEM;
-                       break;
+       trace_seq_printf(s, "%s: ", se->name);
+
+       for (i = 0, n_u64 = 0; i < se->n_fields; i++) {
+               if (trace_seq_has_overflowed(s))
+                       goto end;
+
+               fmt = synth_field_fmt(se->fields[i]->type);
+
+               /* parameter types */
+               if (tr->trace_flags & TRACE_ITER_VERBOSE)
+                       trace_seq_printf(s, "%s ", fmt);
+
+               snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt);
+
+               /* parameter values */
+               if (se->fields[i]->is_string) {
+                       trace_seq_printf(s, print_fmt, se->fields[i]->name,
+                                        (char *)&entry->fields[n_u64],
+                                        i == se->n_fields - 1 ? "" : " ");
+                       n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+               } else {
+                       trace_seq_printf(s, print_fmt, se->fields[i]->name,
+                                        entry->fields[n_u64],
+                                        i == se->n_fields - 1 ? "" : " ");
+                       n_u64++;
                }
        }
+end:
+       trace_seq_putc(s, '\n');
 
-       return 0;
+       return trace_handle_return(s);
 }
 
-static void hist_trigger_elt_comm_copy(struct tracing_map_elt *to,
-                                      struct tracing_map_elt *from)
+static struct trace_event_functions synth_event_funcs = {
+       .trace          = print_synth_event
+};
+
+static notrace void trace_event_raw_event_synth(void *__data,
+                                               u64 *var_ref_vals,
+                                               unsigned int var_ref_idx)
 {
-       char *comm_from = from->private_data;
-       char *comm_to = to->private_data;
+       struct trace_event_file *trace_file = __data;
+       struct synth_trace_event *entry;
+       struct trace_event_buffer fbuffer;
+       struct ring_buffer *buffer;
+       struct synth_event *event;
+       unsigned int i, n_u64;
+       int fields_size = 0;
+
+       event = trace_file->event_call->data;
+
+       if (trace_trigger_soft_disabled(trace_file))
+               return;
+
+       fields_size = event->n_u64 * sizeof(u64);
+
+       /*
+        * Avoid ring buffer recursion detection, as this event
+        * is being performed within another event.
+        */
+       buffer = trace_file->tr->trace_buffer.buffer;
+       ring_buffer_nest_start(buffer);
+
+       entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+                                          sizeof(*entry) + fields_size);
+       if (!entry)
+               goto out;
+
+       for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+               if (event->fields[i]->is_string) {
+                       char *str_val = (char *)(long)var_ref_vals[var_ref_idx + i];
+                       char *str_field = (char *)&entry->fields[n_u64];
+
+                       strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+                       n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+               } else {
+                       entry->fields[n_u64] = var_ref_vals[var_ref_idx + i];
+                       n_u64++;
+               }
+       }
+
+       trace_event_buffer_commit(&fbuffer);
+out:
+       ring_buffer_nest_end(buffer);
+}
 
-       if (comm_from)
-               memcpy(comm_to, comm_from, TASK_COMM_LEN + 1);
+static void free_synth_event_print_fmt(struct trace_event_call *call)
+{
+       if (call) {
+               kfree(call->print_fmt);
+               call->print_fmt = NULL;
+       }
 }
 
-static void hist_trigger_elt_comm_init(struct tracing_map_elt *elt)
+static int __set_synth_event_print_fmt(struct synth_event *event,
+                                      char *buf, int len)
 {
-       char *comm = elt->private_data;
+       const char *fmt;
+       int pos = 0;
+       int i;
+
+       /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+       pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+       for (i = 0; i < event->n_fields; i++) {
+               fmt = synth_field_fmt(event->fields[i]->type);
+               pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s%s",
+                               event->fields[i]->name, fmt,
+                               i == event->n_fields - 1 ? "" : ", ");
+       }
+       pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+       for (i = 0; i < event->n_fields; i++) {
+               pos += snprintf(buf + pos, LEN_OR_ZERO,
+                               ", REC->%s", event->fields[i]->name);
+       }
+
+#undef LEN_OR_ZERO
 
-       if (comm)
-               save_comm(comm, current);
+       /* return the length of print_fmt */
+       return pos;
 }
 
-static const struct tracing_map_ops hist_trigger_elt_comm_ops = {
-       .elt_alloc      = hist_trigger_elt_comm_alloc,
-       .elt_copy       = hist_trigger_elt_comm_copy,
-       .elt_free       = hist_trigger_elt_comm_free,
-       .elt_init       = hist_trigger_elt_comm_init,
-};
+static int set_synth_event_print_fmt(struct trace_event_call *call)
+{
+       struct synth_event *event = call->data;
+       char *print_fmt;
+       int len;
+
+       /* First: called with 0 length to calculate the needed length */
+       len = __set_synth_event_print_fmt(event, NULL, 0);
+
+       print_fmt = kmalloc(len + 1, GFP_KERNEL);
+       if (!print_fmt)
+               return -ENOMEM;
+
+       /* Second: actually write the @print_fmt */
+       __set_synth_event_print_fmt(event, print_fmt, len + 1);
+       call->print_fmt = print_fmt;
 
-static void destroy_hist_field(struct hist_field *hist_field)
+       return 0;
+}
+
+static void free_synth_field(struct synth_field *field)
 {
-       kfree(hist_field);
+       kfree(field->type);
+       kfree(field->name);
+       kfree(field);
 }
 
-static struct hist_field *create_hist_field(struct ftrace_event_field *field,
-                                           unsigned long flags)
+static struct synth_field *parse_synth_field(char *field_type,
+                                            char *field_name)
 {
-       struct hist_field *hist_field;
+       struct synth_field *field;
+       int len, ret = 0;
+       char *array;
 
-       if (field && is_function_field(field))
-               return NULL;
+       if (field_type[0] == ';')
+               field_type++;
 
-       hist_field = kzalloc(sizeof(struct hist_field), GFP_KERNEL);
-       if (!hist_field)
-               return NULL;
+       len = strlen(field_name);
+       if (field_name[len - 1] == ';')
+               field_name[len - 1] = '\0';
 
-       if (flags & HIST_FIELD_FL_HITCOUNT) {
-               hist_field->fn = hist_field_counter;
-               goto out;
+       field = kzalloc(sizeof(*field), GFP_KERNEL);
+       if (!field)
+               return ERR_PTR(-ENOMEM);
+
+       len = strlen(field_type) + 1;
+       array = strchr(field_name, '[');
+       if (array)
+               len += strlen(array);
+       field->type = kzalloc(len, GFP_KERNEL);
+       if (!field->type) {
+               ret = -ENOMEM;
+               goto free;
+       }
+       strcat(field->type, field_type);
+       if (array) {
+               strcat(field->type, array);
+               *array = '\0';
        }
 
-       if (flags & HIST_FIELD_FL_STACKTRACE) {
-               hist_field->fn = hist_field_none;
-               goto out;
+       field->size = synth_field_size(field->type);
+       if (!field->size) {
+               ret = -EINVAL;
+               goto free;
        }
 
-       if (flags & HIST_FIELD_FL_LOG2) {
-               hist_field->fn = hist_field_log2;
-               goto out;
+       if (synth_field_is_string(field->type))
+               field->is_string = true;
+
+       field->is_signed = synth_field_signed(field->type);
+
+       field->name = kstrdup(field_name, GFP_KERNEL);
+       if (!field->name) {
+               ret = -ENOMEM;
+               goto free;
+       }
+ out:
+       return field;
+ free:
+       free_synth_field(field);
+       field = ERR_PTR(ret);
+       goto out;
+}
+
+static void free_synth_tracepoint(struct tracepoint *tp)
+{
+       if (!tp)
+               return;
+
+       kfree(tp->name);
+       kfree(tp);
+}
+
+static struct tracepoint *alloc_synth_tracepoint(char *name)
+{
+       struct tracepoint *tp;
+
+       tp = kzalloc(sizeof(*tp), GFP_KERNEL);
+       if (!tp)
+               return ERR_PTR(-ENOMEM);
+
+       tp->name = kstrdup(name, GFP_KERNEL);
+       if (!tp->name) {
+               kfree(tp);
+               return ERR_PTR(-ENOMEM);
+       }
+
+       return tp;
+}
+
+typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals,
+                                   unsigned int var_ref_idx);
+
+static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
+                              unsigned int var_ref_idx)
+{
+       struct tracepoint *tp = event->tp;
+
+       if (unlikely(atomic_read(&tp->key.enabled) > 0)) {
+               struct tracepoint_func *probe_func_ptr;
+               synth_probe_func_t probe_func;
+               void *__data;
+
+               if (!(cpu_online(raw_smp_processor_id())))
+                       return;
+
+               probe_func_ptr = rcu_dereference_sched((tp)->funcs);
+               if (probe_func_ptr) {
+                       do {
+                               probe_func = probe_func_ptr->func;
+                               __data = probe_func_ptr->data;
+                               probe_func(__data, var_ref_vals, var_ref_idx);
+                       } while ((++probe_func_ptr)->func);
+               }
+       }
+}
+
+static struct synth_event *find_synth_event(const char *name)
+{
+       struct synth_event *event;
+
+       list_for_each_entry(event, &synth_event_list, list) {
+               if (strcmp(event->name, name) == 0)
+                       return event;
+       }
+
+       return NULL;
+}
+
+static int register_synth_event(struct synth_event *event)
+{
+       struct trace_event_call *call = &event->call;
+       int ret = 0;
+
+       event->call.class = &event->class;
+       event->class.system = kstrdup(SYNTH_SYSTEM, GFP_KERNEL);
+       if (!event->class.system) {
+               ret = -ENOMEM;
+               goto out;
+       }
+
+       event->tp = alloc_synth_tracepoint(event->name);
+       if (IS_ERR(event->tp)) {
+               ret = PTR_ERR(event->tp);
+               event->tp = NULL;
+               goto out;
+       }
+
+       INIT_LIST_HEAD(&call->class->fields);
+       call->event.funcs = &synth_event_funcs;
+       call->class->define_fields = synth_event_define_fields;
+
+       ret = register_trace_event(&call->event);
+       if (!ret) {
+               ret = -ENODEV;
+               goto out;
+       }
+       call->flags = TRACE_EVENT_FL_TRACEPOINT;
+       call->class->reg = trace_event_reg;
+       call->class->probe = trace_event_raw_event_synth;
+       call->data = event;
+       call->tp = event->tp;
+
+       ret = trace_add_event_call(call);
+       if (ret) {
+               pr_warn("Failed to register synthetic event: %s\n",
+                       trace_event_name(call));
+               goto err;
+       }
+
+       ret = set_synth_event_print_fmt(call);
+       if (ret < 0) {
+               trace_remove_event_call(call);
+               goto err;
+       }
+ out:
+       return ret;
+ err:
+       unregister_trace_event(&call->event);
+       goto out;
+}
+
+static int unregister_synth_event(struct synth_event *event)
+{
+       struct trace_event_call *call = &event->call;
+       int ret;
+
+       ret = trace_remove_event_call(call);
+
+       return ret;
+}
+
+static void free_synth_event(struct synth_event *event)
+{
+       unsigned int i;
+
+       if (!event)
+               return;
+
+       for (i = 0; i < event->n_fields; i++)
+               free_synth_field(event->fields[i]);
+
+       kfree(event->fields);
+       kfree(event->name);
+       kfree(event->class.system);
+       free_synth_tracepoint(event->tp);
+       free_synth_event_print_fmt(&event->call);
+       kfree(event);
+}
+
+static struct synth_event *alloc_synth_event(char *event_name, int n_fields,
+                                            struct synth_field **fields)
+{
+       struct synth_event *event;
+       unsigned int i;
+
+       event = kzalloc(sizeof(*event), GFP_KERNEL);
+       if (!event) {
+               event = ERR_PTR(-ENOMEM);
+               goto out;
+       }
+
+       event->name = kstrdup(event_name, GFP_KERNEL);
+       if (!event->name) {
+               kfree(event);
+               event = ERR_PTR(-ENOMEM);
+               goto out;
+       }
+
+       event->fields = kcalloc(n_fields, sizeof(*event->fields), GFP_KERNEL);
+       if (!event->fields) {
+               free_synth_event(event);
+               event = ERR_PTR(-ENOMEM);
+               goto out;
+       }
+
+       for (i = 0; i < n_fields; i++)
+               event->fields[i] = fields[i];
+
+       event->n_fields = n_fields;
+ out:
+       return event;
+}
+
+static void action_trace(struct hist_trigger_data *hist_data,
+                        struct tracing_map_elt *elt, void *rec,
+                        struct ring_buffer_event *rbe,
+                        struct action_data *data, u64 *var_ref_vals)
+{
+       struct synth_event *event = data->onmatch.synth_event;
+
+       trace_synth(event, var_ref_vals, data->onmatch.var_ref_idx);
+}
+
+struct hist_var_data {
+       struct list_head list;
+       struct hist_trigger_data *hist_data;
+};
+
+static void add_or_delete_synth_event(struct synth_event *event, int delete)
+{
+       if (delete)
+               free_synth_event(event);
+       else {
+               mutex_lock(&synth_event_mutex);
+               if (!find_synth_event(event->name))
+                       list_add(&event->list, &synth_event_list);
+               else
+                       free_synth_event(event);
+               mutex_unlock(&synth_event_mutex);
+       }
+}
+
+static int create_synth_event(int argc, char **argv)
+{
+       struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
+       struct synth_event *event = NULL;
+       bool delete_event = false;
+       int i, n_fields = 0, ret = 0;
+       char *name;
+
+       mutex_lock(&synth_event_mutex);
+
+       /*
+        * Argument syntax:
+        *  - Add synthetic event: <event_name> field[;field] ...
+        *  - Remove synthetic event: !<event_name> field[;field] ...
+        *      where 'field' = type field_name
+        */
+       if (argc < 1) {
+               ret = -EINVAL;
+               goto out;
+       }
+
+       name = argv[0];
+       if (name[0] == '!') {
+               delete_event = true;
+               name++;
+       }
+
+       event = find_synth_event(name);
+       if (event) {
+               if (delete_event) {
+                       if (event->ref) {
+                               event = NULL;
+                               ret = -EBUSY;
+                               goto out;
+                       }
+                       list_del(&event->list);
+                       goto out;
+               }
+               event = NULL;
+               ret = -EEXIST;
+               goto out;
+       } else if (delete_event)
+               goto out;
+
+       if (argc < 2) {
+               ret = -EINVAL;
+               goto out;
+       }
+
+       for (i = 1; i < argc - 1; i++) {
+               if (strcmp(argv[i], ";") == 0)
+                       continue;
+               if (n_fields == SYNTH_FIELDS_MAX) {
+                       ret = -EINVAL;
+                       goto err;
+               }
+
+               field = parse_synth_field(argv[i], argv[i + 1]);
+               if (IS_ERR(field)) {
+                       ret = PTR_ERR(field);
+                       goto err;
+               }
+               fields[n_fields] = field;
+               i++; n_fields++;
+       }
+
+       if (i < argc) {
+               ret = -EINVAL;
+               goto err;
+       }
+
+       event = alloc_synth_event(name, n_fields, fields);
+       if (IS_ERR(event)) {
+               ret = PTR_ERR(event);
+               event = NULL;
+               goto err;
+       }
+ out:
+       mutex_unlock(&synth_event_mutex);
+
+       if (event) {
+               if (delete_event) {
+                       ret = unregister_synth_event(event);
+                       add_or_delete_synth_event(event, !ret);
+               } else {
+                       ret = register_synth_event(event);
+                       add_or_delete_synth_event(event, ret);
+               }
+       }
+
+       return ret;
+ err:
+       mutex_unlock(&synth_event_mutex);
+
+       for (i = 0; i < n_fields; i++)
+               free_synth_field(fields[i]);
+       free_synth_event(event);
+
+       return ret;
+}
+
+static int release_all_synth_events(void)
+{
+       struct list_head release_events;
+       struct synth_event *event, *e;
+       int ret = 0;
+
+       INIT_LIST_HEAD(&release_events);
+
+       mutex_lock(&synth_event_mutex);
+
+       list_for_each_entry(event, &synth_event_list, list) {
+               if (event->ref) {
+                       mutex_unlock(&synth_event_mutex);
+                       return -EBUSY;
+               }
+       }
+
+       list_splice_init(&event->list, &release_events);
+
+       mutex_unlock(&synth_event_mutex);
+
+       list_for_each_entry_safe(event, e, &release_events, list) {
+               list_del(&event->list);
+
+               ret = unregister_synth_event(event);
+               add_or_delete_synth_event(event, !ret);
+       }
+
+       return ret;
+}
+
+
+static void *synth_events_seq_start(struct seq_file *m, loff_t *pos)
+{
+       mutex_lock(&synth_event_mutex);
+
+       return seq_list_start(&synth_event_list, *pos);
+}
+
+static void *synth_events_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+       return seq_list_next(v, &synth_event_list, pos);
+}
+
+static void synth_events_seq_stop(struct seq_file *m, void *v)
+{
+       mutex_unlock(&synth_event_mutex);
+}
+
+static int synth_events_seq_show(struct seq_file *m, void *v)
+{
+       struct synth_field *field;
+       struct synth_event *event = v;
+       unsigned int i;
+
+       seq_printf(m, "%s\t", event->name);
+
+       for (i = 0; i < event->n_fields; i++) {
+               field = event->fields[i];
+
+               /* parameter values */
+               seq_printf(m, "%s %s%s", field->type, field->name,
+                          i == event->n_fields - 1 ? "" : "; ");
+       }
+
+       seq_putc(m, '\n');
+
+       return 0;
+}
+
+static const struct seq_operations synth_events_seq_op = {
+       .start  = synth_events_seq_start,
+       .next   = synth_events_seq_next,
+       .stop   = synth_events_seq_stop,
+       .show   = synth_events_seq_show
+};
+
+static int synth_events_open(struct inode *inode, struct file *file)
+{
+       int ret;
+
+       if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+               ret = release_all_synth_events();
+               if (ret < 0)
+                       return ret;
+       }
+
+       return seq_open(file, &synth_events_seq_op);
+}
+
+static ssize_t synth_events_write(struct file *file,
+                                 const char __user *buffer,
+                                 size_t count, loff_t *ppos)
+{
+       return trace_parse_run_command(file, buffer, count, ppos,
+                                      create_synth_event);
+}
+
+static const struct file_operations synth_events_fops = {
+       .open           = synth_events_open,
+       .write          = synth_events_write,
+       .read           = seq_read,
+       .llseek         = seq_lseek,
+       .release        = seq_release,
+};
+
+static u64 hist_field_timestamp(struct hist_field *hist_field,
+                               struct tracing_map_elt *elt,
+                               struct ring_buffer_event *rbe,
+                               void *event)
+{
+       struct hist_trigger_data *hist_data = hist_field->hist_data;
+       struct trace_array *tr = hist_data->event_file->tr;
+
+       u64 ts = ring_buffer_event_time_stamp(rbe);
+
+       if (hist_data->attrs->ts_in_usecs && trace_clock_in_ns(tr))
+               ts = ns2usecs(ts);
+
+       return ts;
+}
+
+static u64 hist_field_cpu(struct hist_field *hist_field,
+                         struct tracing_map_elt *elt,
+                         struct ring_buffer_event *rbe,
+                         void *event)
+{
+       int cpu = smp_processor_id();
+
+       return cpu;
+}
+
+static struct hist_field *
+check_field_for_var_ref(struct hist_field *hist_field,
+                       struct hist_trigger_data *var_data,
+                       unsigned int var_idx)
+{
+       struct hist_field *found = NULL;
+
+       if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR_REF) {
+               if (hist_field->var.idx == var_idx &&
+                   hist_field->var.hist_data == var_data) {
+                       found = hist_field;
+               }
+       }
+
+       return found;
+}
+
+static struct hist_field *
+check_field_for_var_refs(struct hist_trigger_data *hist_data,
+                        struct hist_field *hist_field,
+                        struct hist_trigger_data *var_data,
+                        unsigned int var_idx,
+                        unsigned int level)
+{
+       struct hist_field *found = NULL;
+       unsigned int i;
+
+       if (level > 3)
+               return found;
+
+       if (!hist_field)
+               return found;
+
+       found = check_field_for_var_ref(hist_field, var_data, var_idx);
+       if (found)
+               return found;
+
+       for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++) {
+               struct hist_field *operand;
+
+               operand = hist_field->operands[i];
+               found = check_field_for_var_refs(hist_data, operand, var_data,
+                                                var_idx, level + 1);
+               if (found)
+                       return found;
+       }
+
+       return found;
+}
+
+static struct hist_field *find_var_ref(struct hist_trigger_data *hist_data,
+                                      struct hist_trigger_data *var_data,
+                                      unsigned int var_idx)
+{
+       struct hist_field *hist_field, *found = NULL;
+       unsigned int i;
+
+       for_each_hist_field(i, hist_data) {
+               hist_field = hist_data->fields[i];
+               found = check_field_for_var_refs(hist_data, hist_field,
+                                                var_data, var_idx, 0);
+               if (found)
+                       return found;
+       }
+
+       for (i = 0; i < hist_data->n_synth_var_refs; i++) {
+               hist_field = hist_data->synth_var_refs[i];
+               found = check_field_for_var_refs(hist_data, hist_field,
+                                                var_data, var_idx, 0);
+               if (found)
+                       return found;
+       }
+
+       return found;
+}
+
+static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data,
+                                          unsigned int var_idx)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct hist_field *found = NULL;
+       struct hist_var_data *var_data;
+
+       list_for_each_entry(var_data, &tr->hist_vars, list) {
+               if (var_data->hist_data == hist_data)
+                       continue;
+               found = find_var_ref(var_data->hist_data, hist_data, var_idx);
+               if (found)
+                       break;
+       }
+
+       return found;
+}
+
+static bool check_var_refs(struct hist_trigger_data *hist_data)
+{
+       struct hist_field *field;
+       bool found = false;
+       int i;
+
+       for_each_hist_field(i, hist_data) {
+               field = hist_data->fields[i];
+               if (field && field->flags & HIST_FIELD_FL_VAR) {
+                       if (find_any_var_ref(hist_data, field->var.idx)) {
+                               found = true;
+                               break;
+                       }
+               }
+       }
+
+       return found;
+}
+
+static struct hist_var_data *find_hist_vars(struct hist_trigger_data *hist_data)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct hist_var_data *var_data, *found = NULL;
+
+       list_for_each_entry(var_data, &tr->hist_vars, list) {
+               if (var_data->hist_data == hist_data) {
+                       found = var_data;
+                       break;
+               }
+       }
+
+       return found;
+}
+
+static bool field_has_hist_vars(struct hist_field *hist_field,
+                               unsigned int level)
+{
+       int i;
+
+       if (level > 3)
+               return false;
+
+       if (!hist_field)
+               return false;
+
+       if (hist_field->flags & HIST_FIELD_FL_VAR ||
+           hist_field->flags & HIST_FIELD_FL_VAR_REF)
+               return true;
+
+       for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++) {
+               struct hist_field *operand;
+
+               operand = hist_field->operands[i];
+               if (field_has_hist_vars(operand, level + 1))
+                       return true;
+       }
+
+       return false;
+}
+
+static bool has_hist_vars(struct hist_trigger_data *hist_data)
+{
+       struct hist_field *hist_field;
+       int i;
+
+       for_each_hist_field(i, hist_data) {
+               hist_field = hist_data->fields[i];
+               if (field_has_hist_vars(hist_field, 0))
+                       return true;
+       }
+
+       return false;
+}
+
+static int save_hist_vars(struct hist_trigger_data *hist_data)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct hist_var_data *var_data;
+
+       var_data = find_hist_vars(hist_data);
+       if (var_data)
+               return 0;
+
+       if (trace_array_get(tr) < 0)
+               return -ENODEV;
+
+       var_data = kzalloc(sizeof(*var_data), GFP_KERNEL);
+       if (!var_data) {
+               trace_array_put(tr);
+               return -ENOMEM;
+       }
+
+       var_data->hist_data = hist_data;
+       list_add(&var_data->list, &tr->hist_vars);
+
+       return 0;
+}
+
+static void remove_hist_vars(struct hist_trigger_data *hist_data)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct hist_var_data *var_data;
+
+       var_data = find_hist_vars(hist_data);
+       if (!var_data)
+               return;
+
+       if (WARN_ON(check_var_refs(hist_data)))
+               return;
+
+       list_del(&var_data->list);
+
+       kfree(var_data);
+
+       trace_array_put(tr);
+}
+
+static struct hist_field *find_var_field(struct hist_trigger_data *hist_data,
+                                        const char *var_name)
+{
+       struct hist_field *hist_field, *found = NULL;
+       int i;
+
+       for_each_hist_field(i, hist_data) {
+               hist_field = hist_data->fields[i];
+               if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR &&
+                   strcmp(hist_field->var.name, var_name) == 0) {
+                       found = hist_field;
+                       break;
+               }
+       }
+
+       return found;
+}
+
+static struct hist_field *find_var(struct hist_trigger_data *hist_data,
+                                  struct trace_event_file *file,
+                                  const char *var_name)
+{
+       struct hist_trigger_data *test_data;
+       struct event_trigger_data *test;
+       struct hist_field *hist_field;
+
+       hist_field = find_var_field(hist_data, var_name);
+       if (hist_field)
+               return hist_field;
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       test_data = test->private_data;
+                       hist_field = find_var_field(test_data, var_name);
+                       if (hist_field)
+                               return hist_field;
+               }
+       }
+
+       return NULL;
+}
+
+static struct trace_event_file *find_var_file(struct trace_array *tr,
+                                             char *system,
+                                             char *event_name,
+                                             char *var_name)
+{
+       struct hist_trigger_data *var_hist_data;
+       struct hist_var_data *var_data;
+       struct trace_event_file *file, *found = NULL;
+
+       if (system)
+               return find_event_file(tr, system, event_name);
+
+       list_for_each_entry(var_data, &tr->hist_vars, list) {
+               var_hist_data = var_data->hist_data;
+               file = var_hist_data->event_file;
+               if (file == found)
+                       continue;
+
+               if (find_var_field(var_hist_data, var_name)) {
+                       if (found) {
+                               hist_err_event("Variable name not unique, need to use fully qualified name (subsys.event.var) for variable: ", system, event_name, var_name);
+                               return NULL;
+                       }
+
+                       found = file;
+               }
+       }
+
+       return found;
+}
+
+static struct hist_field *find_file_var(struct trace_event_file *file,
+                                       const char *var_name)
+{
+       struct hist_trigger_data *test_data;
+       struct event_trigger_data *test;
+       struct hist_field *hist_field;
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       test_data = test->private_data;
+                       hist_field = find_var_field(test_data, var_name);
+                       if (hist_field)
+                               return hist_field;
+               }
+       }
+
+       return NULL;
+}
+
+static struct hist_field *
+find_match_var(struct hist_trigger_data *hist_data, char *var_name)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct hist_field *hist_field, *found = NULL;
+       struct trace_event_file *file;
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_actions; i++) {
+               struct action_data *data = hist_data->actions[i];
+
+               if (data->fn == action_trace) {
+                       char *system = data->onmatch.match_event_system;
+                       char *event_name = data->onmatch.match_event;
+
+                       file = find_var_file(tr, system, event_name, var_name);
+                       if (!file)
+                               continue;
+                       hist_field = find_file_var(file, var_name);
+                       if (hist_field) {
+                               if (found) {
+                                       hist_err_event("Variable name not unique, need to use fully qualified name (subsys.event.var) for variable: ", system, event_name, var_name);
+                                       return ERR_PTR(-EINVAL);
+                               }
+
+                               found = hist_field;
+                       }
+               }
+       }
+       return found;
+}
+
+static struct hist_field *find_event_var(struct hist_trigger_data *hist_data,
+                                        char *system,
+                                        char *event_name,
+                                        char *var_name)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct hist_field *hist_field = NULL;
+       struct trace_event_file *file;
+
+       if (!system || !event_name) {
+               hist_field = find_match_var(hist_data, var_name);
+               if (IS_ERR(hist_field))
+                       return NULL;
+               if (hist_field)
+                       return hist_field;
+       }
+
+       file = find_var_file(tr, system, event_name, var_name);
+       if (!file)
+               return NULL;
+
+       hist_field = find_file_var(file, var_name);
+
+       return hist_field;
+}
+
+struct hist_elt_data {
+       char *comm;
+       u64 *var_ref_vals;
+       char *field_var_str[SYNTH_FIELDS_MAX];
+};
+
+static u64 hist_field_var_ref(struct hist_field *hist_field,
+                             struct tracing_map_elt *elt,
+                             struct ring_buffer_event *rbe,
+                             void *event)
+{
+       struct hist_elt_data *elt_data;
+       u64 var_val = 0;
+
+       elt_data = elt->private_data;
+       var_val = elt_data->var_ref_vals[hist_field->var_ref_idx];
+
+       return var_val;
+}
+
+static bool resolve_var_refs(struct hist_trigger_data *hist_data, void *key,
+                            u64 *var_ref_vals, bool self)
+{
+       struct hist_trigger_data *var_data;
+       struct tracing_map_elt *var_elt;
+       struct hist_field *hist_field;
+       unsigned int i, var_idx;
+       bool resolved = true;
+       u64 var_val = 0;
+
+       for (i = 0; i < hist_data->n_var_refs; i++) {
+               hist_field = hist_data->var_refs[i];
+               var_idx = hist_field->var.idx;
+               var_data = hist_field->var.hist_data;
+
+               if (var_data == NULL) {
+                       resolved = false;
+                       break;
+               }
+
+               if ((self && var_data != hist_data) ||
+                   (!self && var_data == hist_data))
+                       continue;
+
+               var_elt = tracing_map_lookup(var_data->map, key);
+               if (!var_elt) {
+                       resolved = false;
+                       break;
+               }
+
+               if (!tracing_map_var_set(var_elt, var_idx)) {
+                       resolved = false;
+                       break;
+               }
+
+               if (self || !hist_field->read_once)
+                       var_val = tracing_map_read_var(var_elt, var_idx);
+               else
+                       var_val = tracing_map_read_var_once(var_elt, var_idx);
+
+               var_ref_vals[i] = var_val;
+       }
+
+       return resolved;
+}
+
+static const char *hist_field_name(struct hist_field *field,
+                                  unsigned int level)
+{
+       const char *field_name = "";
+
+       if (level > 1)
+               return field_name;
+
+       if (field->field)
+               field_name = field->field->name;
+       else if (field->flags & HIST_FIELD_FL_LOG2 ||
+                field->flags & HIST_FIELD_FL_ALIAS)
+               field_name = hist_field_name(field->operands[0], ++level);
+       else if (field->flags & HIST_FIELD_FL_CPU)
+               field_name = "cpu";
+       else if (field->flags & HIST_FIELD_FL_EXPR ||
+                field->flags & HIST_FIELD_FL_VAR_REF) {
+               if (field->system) {
+                       static char full_name[MAX_FILTER_STR_VAL];
+
+                       strcat(full_name, field->system);
+                       strcat(full_name, ".");
+                       strcat(full_name, field->event_name);
+                       strcat(full_name, ".");
+                       strcat(full_name, field->name);
+                       field_name = full_name;
+               } else
+                       field_name = field->name;
+       } else if (field->flags & HIST_FIELD_FL_TIMESTAMP)
+               field_name = "common_timestamp";
+
+       if (field_name == NULL)
+               field_name = "";
+
+       return field_name;
+}
+
+static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
+{
+       hist_field_fn_t fn = NULL;
+
+       switch (field_size) {
+       case 8:
+               if (field_is_signed)
+                       fn = hist_field_s64;
+               else
+                       fn = hist_field_u64;
+               break;
+       case 4:
+               if (field_is_signed)
+                       fn = hist_field_s32;
+               else
+                       fn = hist_field_u32;
+               break;
+       case 2:
+               if (field_is_signed)
+                       fn = hist_field_s16;
+               else
+                       fn = hist_field_u16;
+               break;
+       case 1:
+               if (field_is_signed)
+                       fn = hist_field_s8;
+               else
+                       fn = hist_field_u8;
+               break;
+       }
+
+       return fn;
+}
+
+static int parse_map_size(char *str)
+{
+       unsigned long size, map_bits;
+       int ret;
+
+       strsep(&str, "=");
+       if (!str) {
+               ret = -EINVAL;
+               goto out;
+       }
+
+       ret = kstrtoul(str, 0, &size);
+       if (ret)
+               goto out;
+
+       map_bits = ilog2(roundup_pow_of_two(size));
+       if (map_bits < TRACING_MAP_BITS_MIN ||
+           map_bits > TRACING_MAP_BITS_MAX)
+               ret = -EINVAL;
+       else
+               ret = map_bits;
+ out:
+       return ret;
+}
+
+static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
+{
+       unsigned int i;
+
+       if (!attrs)
+               return;
+
+       for (i = 0; i < attrs->n_assignments; i++)
+               kfree(attrs->assignment_str[i]);
+
+       for (i = 0; i < attrs->n_actions; i++)
+               kfree(attrs->action_str[i]);
+
+       kfree(attrs->name);
+       kfree(attrs->sort_key_str);
+       kfree(attrs->keys_str);
+       kfree(attrs->vals_str);
+       kfree(attrs->clock);
+       kfree(attrs);
+}
+
+static int parse_action(char *str, struct hist_trigger_attrs *attrs)
+{
+       int ret = -EINVAL;
+
+       if (attrs->n_actions >= HIST_ACTIONS_MAX)
+               return ret;
+
+       if ((strncmp(str, "onmatch(", strlen("onmatch(")) == 0) ||
+           (strncmp(str, "onmax(", strlen("onmax(")) == 0)) {
+               attrs->action_str[attrs->n_actions] = kstrdup(str, GFP_KERNEL);
+               if (!attrs->action_str[attrs->n_actions]) {
+                       ret = -ENOMEM;
+                       return ret;
+               }
+               attrs->n_actions++;
+               ret = 0;
+       }
+
+       return ret;
+}
+
+static int parse_assignment(char *str, struct hist_trigger_attrs *attrs)
+{
+       int ret = 0;
+
+       if ((strncmp(str, "key=", strlen("key=")) == 0) ||
+           (strncmp(str, "keys=", strlen("keys=")) == 0)) {
+               attrs->keys_str = kstrdup(str, GFP_KERNEL);
+               if (!attrs->keys_str) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+       } else if ((strncmp(str, "val=", strlen("val=")) == 0) ||
+                (strncmp(str, "vals=", strlen("vals=")) == 0) ||
+                (strncmp(str, "values=", strlen("values=")) == 0)) {
+               attrs->vals_str = kstrdup(str, GFP_KERNEL);
+               if (!attrs->vals_str) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+       } else if (strncmp(str, "sort=", strlen("sort=")) == 0) {
+               attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
+               if (!attrs->sort_key_str) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+       } else if (strncmp(str, "name=", strlen("name=")) == 0) {
+               attrs->name = kstrdup(str, GFP_KERNEL);
+               if (!attrs->name) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+       } else if (strncmp(str, "clock=", strlen("clock=")) == 0) {
+               strsep(&str, "=");
+               if (!str) {
+                       ret = -EINVAL;
+                       goto out;
+               }
+
+               str = strstrip(str);
+               attrs->clock = kstrdup(str, GFP_KERNEL);
+               if (!attrs->clock) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+       } else if (strncmp(str, "size=", strlen("size=")) == 0) {
+               int map_bits = parse_map_size(str);
+
+               if (map_bits < 0) {
+                       ret = map_bits;
+                       goto out;
+               }
+               attrs->map_bits = map_bits;
+       } else {
+               char *assignment;
+
+               if (attrs->n_assignments == TRACING_MAP_VARS_MAX) {
+                       hist_err("Too many variables defined: ", str);
+                       ret = -EINVAL;
+                       goto out;
+               }
+
+               assignment = kstrdup(str, GFP_KERNEL);
+               if (!assignment) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+
+               attrs->assignment_str[attrs->n_assignments++] = assignment;
+       }
+ out:
+       return ret;
+}
+
+static struct hist_trigger_attrs *parse_hist_trigger_attrs(char *trigger_str)
+{
+       struct hist_trigger_attrs *attrs;
+       int ret = 0;
+
+       attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
+       if (!attrs)
+               return ERR_PTR(-ENOMEM);
+
+       while (trigger_str) {
+               char *str = strsep(&trigger_str, ":");
+
+               if (strchr(str, '=')) {
+                       ret = parse_assignment(str, attrs);
+                       if (ret)
+                               goto free;
+               } else if (strcmp(str, "pause") == 0)
+                       attrs->pause = true;
+               else if ((strcmp(str, "cont") == 0) ||
+                        (strcmp(str, "continue") == 0))
+                       attrs->cont = true;
+               else if (strcmp(str, "clear") == 0)
+                       attrs->clear = true;
+               else {
+                       ret = parse_action(str, attrs);
+                       if (ret)
+                               goto free;
+               }
+       }
+
+       if (!attrs->keys_str) {
+               ret = -EINVAL;
+               goto free;
+       }
+
+       if (!attrs->clock) {
+               attrs->clock = kstrdup("global", GFP_KERNEL);
+               if (!attrs->clock) {
+                       ret = -ENOMEM;
+                       goto free;
+               }
+       }
+
+       return attrs;
+ free:
+       destroy_hist_trigger_attrs(attrs);
+
+       return ERR_PTR(ret);
+}
+
+static inline void save_comm(char *comm, struct task_struct *task)
+{
+       if (!task->pid) {
+               strcpy(comm, "<idle>");
+               return;
+       }
+
+       if (WARN_ON_ONCE(task->pid < 0)) {
+               strcpy(comm, "<XXX>");
+               return;
+       }
+
+       memcpy(comm, task->comm, TASK_COMM_LEN);
+}
+
+static void hist_elt_data_free(struct hist_elt_data *elt_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < SYNTH_FIELDS_MAX; i++)
+               kfree(elt_data->field_var_str[i]);
+
+       kfree(elt_data->comm);
+       kfree(elt_data);
+}
+
+static void hist_trigger_elt_data_free(struct tracing_map_elt *elt)
+{
+       struct hist_elt_data *elt_data = elt->private_data;
+
+       hist_elt_data_free(elt_data);
+}
+
+static int hist_trigger_elt_data_alloc(struct tracing_map_elt *elt)
+{
+       struct hist_trigger_data *hist_data = elt->map->private_data;
+       unsigned int size = TASK_COMM_LEN;
+       struct hist_elt_data *elt_data;
+       struct hist_field *key_field;
+       unsigned int i, n_str;
+
+       elt_data = kzalloc(sizeof(*elt_data), GFP_KERNEL);
+       if (!elt_data)
+               return -ENOMEM;
+
+       for_each_hist_key_field(i, hist_data) {
+               key_field = hist_data->fields[i];
+
+               if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
+                       elt_data->comm = kzalloc(size, GFP_KERNEL);
+                       if (!elt_data->comm) {
+                               kfree(elt_data);
+                               return -ENOMEM;
+                       }
+                       break;
+               }
+       }
+
+       n_str = hist_data->n_field_var_str + hist_data->n_max_var_str;
+
+       size = STR_VAR_LEN_MAX;
+
+       for (i = 0; i < n_str; i++) {
+               elt_data->field_var_str[i] = kzalloc(size, GFP_KERNEL);
+               if (!elt_data->field_var_str[i]) {
+                       hist_elt_data_free(elt_data);
+                       return -ENOMEM;
+               }
+       }
+
+       elt->private_data = elt_data;
+
+       return 0;
+}
+
+static void hist_trigger_elt_data_init(struct tracing_map_elt *elt)
+{
+       struct hist_elt_data *elt_data = elt->private_data;
+
+       if (elt_data->comm)
+               save_comm(elt_data->comm, current);
+}
+
+static const struct tracing_map_ops hist_trigger_elt_data_ops = {
+       .elt_alloc      = hist_trigger_elt_data_alloc,
+       .elt_free       = hist_trigger_elt_data_free,
+       .elt_init       = hist_trigger_elt_data_init,
+};
+
+static const char *get_hist_field_flags(struct hist_field *hist_field)
+{
+       const char *flags_str = NULL;
+
+       if (hist_field->flags & HIST_FIELD_FL_HEX)
+               flags_str = "hex";
+       else if (hist_field->flags & HIST_FIELD_FL_SYM)
+               flags_str = "sym";
+       else if (hist_field->flags & HIST_FIELD_FL_SYM_OFFSET)
+               flags_str = "sym-offset";
+       else if (hist_field->flags & HIST_FIELD_FL_EXECNAME)
+               flags_str = "execname";
+       else if (hist_field->flags & HIST_FIELD_FL_SYSCALL)
+               flags_str = "syscall";
+       else if (hist_field->flags & HIST_FIELD_FL_LOG2)
+               flags_str = "log2";
+       else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP_USECS)
+               flags_str = "usecs";
+
+       return flags_str;
+}
+
+static void expr_field_str(struct hist_field *field, char *expr)
+{
+       if (field->flags & HIST_FIELD_FL_VAR_REF)
+               strcat(expr, "$");
+
+       strcat(expr, hist_field_name(field, 0));
+
+       if (field->flags && !(field->flags & HIST_FIELD_FL_VAR_REF)) {
+               const char *flags_str = get_hist_field_flags(field);
+
+               if (flags_str) {
+                       strcat(expr, ".");
+                       strcat(expr, flags_str);
+               }
+       }
+}
+
+static char *expr_str(struct hist_field *field, unsigned int level)
+{
+       char *expr;
+
+       if (level > 1)
+               return NULL;
+
+       expr = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL);
+       if (!expr)
+               return NULL;
+
+       if (!field->operands[0]) {
+               expr_field_str(field, expr);
+               return expr;
+       }
+
+       if (field->operator == FIELD_OP_UNARY_MINUS) {
+               char *subexpr;
+
+               strcat(expr, "-(");
+               subexpr = expr_str(field->operands[0], ++level);
+               if (!subexpr) {
+                       kfree(expr);
+                       return NULL;
+               }
+               strcat(expr, subexpr);
+               strcat(expr, ")");
+
+               kfree(subexpr);
+
+               return expr;
+       }
+
+       expr_field_str(field->operands[0], expr);
+
+       switch (field->operator) {
+       case FIELD_OP_MINUS:
+               strcat(expr, "-");
+               break;
+       case FIELD_OP_PLUS:
+               strcat(expr, "+");
+               break;
+       default:
+               kfree(expr);
+               return NULL;
+       }
+
+       expr_field_str(field->operands[1], expr);
+
+       return expr;
+}
+
+static int contains_operator(char *str)
+{
+       enum field_op_id field_op = FIELD_OP_NONE;
+       char *op;
+
+       op = strpbrk(str, "+-");
+       if (!op)
+               return FIELD_OP_NONE;
+
+       switch (*op) {
+       case '-':
+               if (*str == '-')
+                       field_op = FIELD_OP_UNARY_MINUS;
+               else
+                       field_op = FIELD_OP_MINUS;
+               break;
+       case '+':
+               field_op = FIELD_OP_PLUS;
+               break;
+       default:
+               break;
+       }
+
+       return field_op;
+}
+
+static void destroy_hist_field(struct hist_field *hist_field,
+                              unsigned int level)
+{
+       unsigned int i;
+
+       if (level > 3)
+               return;
+
+       if (!hist_field)
+               return;
+
+       for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++)
+               destroy_hist_field(hist_field->operands[i], level + 1);
+
+       kfree(hist_field->var.name);
+       kfree(hist_field->name);
+       kfree(hist_field->type);
+
+       kfree(hist_field);
+}
+
+static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
+                                           struct ftrace_event_field *field,
+                                           unsigned long flags,
+                                           char *var_name)
+{
+       struct hist_field *hist_field;
+
+       if (field && is_function_field(field))
+               return NULL;
+
+       hist_field = kzalloc(sizeof(struct hist_field), GFP_KERNEL);
+       if (!hist_field)
+               return NULL;
+
+       hist_field->hist_data = hist_data;
+
+       if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
+               goto out; /* caller will populate */
+
+       if (flags & HIST_FIELD_FL_VAR_REF) {
+               hist_field->fn = hist_field_var_ref;
+               goto out;
+       }
+
+       if (flags & HIST_FIELD_FL_HITCOUNT) {
+               hist_field->fn = hist_field_counter;
+               hist_field->size = sizeof(u64);
+               hist_field->type = kstrdup("u64", GFP_KERNEL);
+               if (!hist_field->type)
+                       goto free;
+               goto out;
+       }
+
+       if (flags & HIST_FIELD_FL_STACKTRACE) {
+               hist_field->fn = hist_field_none;
+               goto out;
+       }
+
+       if (flags & HIST_FIELD_FL_LOG2) {
+               unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
+               hist_field->fn = hist_field_log2;
+               hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
+               hist_field->size = hist_field->operands[0]->size;
+               hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL);
+               if (!hist_field->type)
+                       goto free;
+               goto out;
+       }
+
+       if (flags & HIST_FIELD_FL_TIMESTAMP) {
+               hist_field->fn = hist_field_timestamp;
+               hist_field->size = sizeof(u64);
+               hist_field->type = kstrdup("u64", GFP_KERNEL);
+               if (!hist_field->type)
+                       goto free;
+               goto out;
+       }
+
+       if (flags & HIST_FIELD_FL_CPU) {
+               hist_field->fn = hist_field_cpu;
+               hist_field->size = sizeof(int);
+               hist_field->type = kstrdup("unsigned int", GFP_KERNEL);
+               if (!hist_field->type)
+                       goto free;
+               goto out;
+       }
+
+       if (WARN_ON_ONCE(!field))
+               goto out;
+
+       if (is_string_field(field)) {
+               flags |= HIST_FIELD_FL_STRING;
+
+               hist_field->size = MAX_FILTER_STR_VAL;
+               hist_field->type = kstrdup(field->type, GFP_KERNEL);
+               if (!hist_field->type)
+                       goto free;
+
+               if (field->filter_type == FILTER_STATIC_STRING)
+                       hist_field->fn = hist_field_string;
+               else if (field->filter_type == FILTER_DYN_STRING)
+                       hist_field->fn = hist_field_dynstring;
+               else
+                       hist_field->fn = hist_field_pstring;
+       } else {
+               hist_field->size = field->size;
+               hist_field->is_signed = field->is_signed;
+               hist_field->type = kstrdup(field->type, GFP_KERNEL);
+               if (!hist_field->type)
+                       goto free;
+
+               hist_field->fn = select_value_fn(field->size,
+                                                field->is_signed);
+               if (!hist_field->fn) {
+                       destroy_hist_field(hist_field, 0);
+                       return NULL;
+               }
+       }
+ out:
+       hist_field->field = field;
+       hist_field->flags = flags;
+
+       if (var_name) {
+               hist_field->var.name = kstrdup(var_name, GFP_KERNEL);
+               if (!hist_field->var.name)
+                       goto free;
+       }
+
+       return hist_field;
+ free:
+       destroy_hist_field(hist_field, 0);
+       return NULL;
+}
+
+static void destroy_hist_fields(struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < HIST_FIELDS_MAX; i++) {
+               if (hist_data->fields[i]) {
+                       destroy_hist_field(hist_data->fields[i], 0);
+                       hist_data->fields[i] = NULL;
+               }
+       }
+}
+
+static int init_var_ref(struct hist_field *ref_field,
+                       struct hist_field *var_field,
+                       char *system, char *event_name)
+{
+       int err = 0;
+
+       ref_field->var.idx = var_field->var.idx;
+       ref_field->var.hist_data = var_field->hist_data;
+       ref_field->size = var_field->size;
+       ref_field->is_signed = var_field->is_signed;
+       ref_field->flags |= var_field->flags &
+               (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
+
+       if (system) {
+               ref_field->system = kstrdup(system, GFP_KERNEL);
+               if (!ref_field->system)
+                       return -ENOMEM;
+       }
+
+       if (event_name) {
+               ref_field->event_name = kstrdup(event_name, GFP_KERNEL);
+               if (!ref_field->event_name) {
+                       err = -ENOMEM;
+                       goto free;
+               }
+       }
+
+       if (var_field->var.name) {
+               ref_field->name = kstrdup(var_field->var.name, GFP_KERNEL);
+               if (!ref_field->name) {
+                       err = -ENOMEM;
+                       goto free;
+               }
+       } else if (var_field->name) {
+               ref_field->name = kstrdup(var_field->name, GFP_KERNEL);
+               if (!ref_field->name) {
+                       err = -ENOMEM;
+                       goto free;
+               }
+       }
+
+       ref_field->type = kstrdup(var_field->type, GFP_KERNEL);
+       if (!ref_field->type) {
+               err = -ENOMEM;
+               goto free;
+       }
+ out:
+       return err;
+ free:
+       kfree(ref_field->system);
+       kfree(ref_field->event_name);
+       kfree(ref_field->name);
+
+       goto out;
+}
+
+static struct hist_field *create_var_ref(struct hist_field *var_field,
+                                        char *system, char *event_name)
+{
+       unsigned long flags = HIST_FIELD_FL_VAR_REF;
+       struct hist_field *ref_field;
+
+       ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
+       if (ref_field) {
+               if (init_var_ref(ref_field, var_field, system, event_name)) {
+                       destroy_hist_field(ref_field, 0);
+                       return NULL;
+               }
+       }
+
+       return ref_field;
+}
+
+static bool is_var_ref(char *var_name)
+{
+       if (!var_name || strlen(var_name) < 2 || var_name[0] != '$')
+               return false;
+
+       return true;
+}
+
+static char *field_name_from_var(struct hist_trigger_data *hist_data,
+                                char *var_name)
+{
+       char *name, *field;
+       unsigned int i;
+
+       for (i = 0; i < hist_data->attrs->var_defs.n_vars; i++) {
+               name = hist_data->attrs->var_defs.name[i];
+
+               if (strcmp(var_name, name) == 0) {
+                       field = hist_data->attrs->var_defs.expr[i];
+                       if (contains_operator(field) || is_var_ref(field))
+                               continue;
+                       return field;
+               }
+       }
+
+       return NULL;
+}
+
+static char *local_field_var_ref(struct hist_trigger_data *hist_data,
+                                char *system, char *event_name,
+                                char *var_name)
+{
+       struct trace_event_call *call;
+
+       if (system && event_name) {
+               call = hist_data->event_file->event_call;
+
+               if (strcmp(system, call->class->system) != 0)
+                       return NULL;
+
+               if (strcmp(event_name, trace_event_name(call)) != 0)
+                       return NULL;
+       }
+
+       if (!!system != !!event_name)
+               return NULL;
+
+       if (!is_var_ref(var_name))
+               return NULL;
+
+       var_name++;
+
+       return field_name_from_var(hist_data, var_name);
+}
+
+static struct hist_field *parse_var_ref(struct hist_trigger_data *hist_data,
+                                       char *system, char *event_name,
+                                       char *var_name)
+{
+       struct hist_field *var_field = NULL, *ref_field = NULL;
+
+       if (!is_var_ref(var_name))
+               return NULL;
+
+       var_name++;
+
+       var_field = find_event_var(hist_data, system, event_name, var_name);
+       if (var_field)
+               ref_field = create_var_ref(var_field, system, event_name);
+
+       if (!ref_field)
+               hist_err_event("Couldn't find variable: $",
+                              system, event_name, var_name);
+
+       return ref_field;
+}
+
+static struct ftrace_event_field *
+parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
+           char *field_str, unsigned long *flags)
+{
+       struct ftrace_event_field *field = NULL;
+       char *field_name, *modifier, *str;
+
+       modifier = str = kstrdup(field_str, GFP_KERNEL);
+       if (!modifier)
+               return ERR_PTR(-ENOMEM);
+
+       field_name = strsep(&modifier, ".");
+       if (modifier) {
+               if (strcmp(modifier, "hex") == 0)
+                       *flags |= HIST_FIELD_FL_HEX;
+               else if (strcmp(modifier, "sym") == 0)
+                       *flags |= HIST_FIELD_FL_SYM;
+               else if (strcmp(modifier, "sym-offset") == 0)
+                       *flags |= HIST_FIELD_FL_SYM_OFFSET;
+               else if ((strcmp(modifier, "execname") == 0) &&
+                        (strcmp(field_name, "common_pid") == 0))
+                       *flags |= HIST_FIELD_FL_EXECNAME;
+               else if (strcmp(modifier, "syscall") == 0)
+                       *flags |= HIST_FIELD_FL_SYSCALL;
+               else if (strcmp(modifier, "log2") == 0)
+                       *flags |= HIST_FIELD_FL_LOG2;
+               else if (strcmp(modifier, "usecs") == 0)
+                       *flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
+               else {
+                       hist_err("Invalid field modifier: ", modifier);
+                       field = ERR_PTR(-EINVAL);
+                       goto out;
+               }
+       }
+
+       if (strcmp(field_name, "common_timestamp") == 0) {
+               *flags |= HIST_FIELD_FL_TIMESTAMP;
+               hist_data->enable_timestamps = true;
+               if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
+                       hist_data->attrs->ts_in_usecs = true;
+       } else if (strcmp(field_name, "cpu") == 0)
+               *flags |= HIST_FIELD_FL_CPU;
+       else {
+               field = trace_find_event_field(file->event_call, field_name);
+               if (!field || !field->size) {
+                       hist_err("Couldn't find field: ", field_name);
+                       field = ERR_PTR(-EINVAL);
+                       goto out;
+               }
+       }
+ out:
+       kfree(str);
+
+       return field;
+}
+
+static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
+                                      struct hist_field *var_ref,
+                                      char *var_name)
+{
+       struct hist_field *alias = NULL;
+       unsigned long flags = HIST_FIELD_FL_ALIAS | HIST_FIELD_FL_VAR;
+
+       alias = create_hist_field(hist_data, NULL, flags, var_name);
+       if (!alias)
+               return NULL;
+
+       alias->fn = var_ref->fn;
+       alias->operands[0] = var_ref;
+
+       if (init_var_ref(alias, var_ref, var_ref->system, var_ref->event_name)) {
+               destroy_hist_field(alias, 0);
+               return NULL;
+       }
+
+       return alias;
+}
+
+static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
+                                    struct trace_event_file *file, char *str,
+                                    unsigned long *flags, char *var_name)
+{
+       char *s, *ref_system = NULL, *ref_event = NULL, *ref_var = str;
+       struct ftrace_event_field *field = NULL;
+       struct hist_field *hist_field = NULL;
+       int ret = 0;
+
+       s = strchr(str, '.');
+       if (s) {
+               s = strchr(++s, '.');
+               if (s) {
+                       ref_system = strsep(&str, ".");
+                       if (!str) {
+                               ret = -EINVAL;
+                               goto out;
+                       }
+                       ref_event = strsep(&str, ".");
+                       if (!str) {
+                               ret = -EINVAL;
+                               goto out;
+                       }
+                       ref_var = str;
+               }
+       }
+
+       s = local_field_var_ref(hist_data, ref_system, ref_event, ref_var);
+       if (!s) {
+               hist_field = parse_var_ref(hist_data, ref_system, ref_event, ref_var);
+               if (hist_field) {
+                       hist_data->var_refs[hist_data->n_var_refs] = hist_field;
+                       hist_field->var_ref_idx = hist_data->n_var_refs++;
+                       if (var_name) {
+                               hist_field = create_alias(hist_data, hist_field, var_name);
+                               if (!hist_field) {
+                                       ret = -ENOMEM;
+                                       goto out;
+                               }
+                       }
+                       return hist_field;
+               }
+       } else
+               str = s;
+
+       field = parse_field(hist_data, file, str, flags);
+       if (IS_ERR(field)) {
+               ret = PTR_ERR(field);
+               goto out;
+       }
+
+       hist_field = create_hist_field(hist_data, field, *flags, var_name);
+       if (!hist_field) {
+               ret = -ENOMEM;
+               goto out;
+       }
+
+       return hist_field;
+ out:
+       return ERR_PTR(ret);
+}
+
+static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
+                                    struct trace_event_file *file,
+                                    char *str, unsigned long flags,
+                                    char *var_name, unsigned int level);
+
+static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
+                                     struct trace_event_file *file,
+                                     char *str, unsigned long flags,
+                                     char *var_name, unsigned int level)
+{
+       struct hist_field *operand1, *expr = NULL;
+       unsigned long operand_flags;
+       int ret = 0;
+       char *s;
+
+       // we support only -(xxx) i.e. explicit parens required
+
+       if (level > 3) {
+               hist_err("Too many subexpressions (3 max): ", str);
+               ret = -EINVAL;
+               goto free;
+       }
+
+       str++; // skip leading '-'
+
+       s = strchr(str, '(');
+       if (s)
+               str++;
+       else {
+               ret = -EINVAL;
+               goto free;
+       }
+
+       s = strrchr(str, ')');
+       if (s)
+               *s = '\0';
+       else {
+               ret = -EINVAL; // no closing ')'
+               goto free;
+       }
+
+       flags |= HIST_FIELD_FL_EXPR;
+       expr = create_hist_field(hist_data, NULL, flags, var_name);
+       if (!expr) {
+               ret = -ENOMEM;
+               goto free;
+       }
+
+       operand_flags = 0;
+       operand1 = parse_expr(hist_data, file, str, operand_flags, NULL, ++level);
+       if (IS_ERR(operand1)) {
+               ret = PTR_ERR(operand1);
+               goto free;
+       }
+
+       expr->flags |= operand1->flags &
+               (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
+       expr->fn = hist_field_unary_minus;
+       expr->operands[0] = operand1;
+       expr->operator = FIELD_OP_UNARY_MINUS;
+       expr->name = expr_str(expr, 0);
+       expr->type = kstrdup(operand1->type, GFP_KERNEL);
+       if (!expr->type) {
+               ret = -ENOMEM;
+               goto free;
+       }
+
+       return expr;
+ free:
+       destroy_hist_field(expr, 0);
+       return ERR_PTR(ret);
+}
+
+static int check_expr_operands(struct hist_field *operand1,
+                              struct hist_field *operand2)
+{
+       unsigned long operand1_flags = operand1->flags;
+       unsigned long operand2_flags = operand2->flags;
+
+       if ((operand1_flags & HIST_FIELD_FL_VAR_REF) ||
+           (operand1_flags & HIST_FIELD_FL_ALIAS)) {
+               struct hist_field *var;
+
+               var = find_var_field(operand1->var.hist_data, operand1->name);
+               if (!var)
+                       return -EINVAL;
+               operand1_flags = var->flags;
+       }
+
+       if ((operand2_flags & HIST_FIELD_FL_VAR_REF) ||
+           (operand2_flags & HIST_FIELD_FL_ALIAS)) {
+               struct hist_field *var;
+
+               var = find_var_field(operand2->var.hist_data, operand2->name);
+               if (!var)
+                       return -EINVAL;
+               operand2_flags = var->flags;
+       }
+
+       if ((operand1_flags & HIST_FIELD_FL_TIMESTAMP_USECS) !=
+           (operand2_flags & HIST_FIELD_FL_TIMESTAMP_USECS)) {
+               hist_err("Timestamp units in expression don't match", NULL);
+               return -EINVAL;
+       }
+
+       return 0;
+}
+
+static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
+                                    struct trace_event_file *file,
+                                    char *str, unsigned long flags,
+                                    char *var_name, unsigned int level)
+{
+       struct hist_field *operand1 = NULL, *operand2 = NULL, *expr = NULL;
+       unsigned long operand_flags;
+       int field_op, ret = -EINVAL;
+       char *sep, *operand1_str;
+
+       if (level > 3) {
+               hist_err("Too many subexpressions (3 max): ", str);
+               return ERR_PTR(-EINVAL);
+       }
+
+       field_op = contains_operator(str);
+
+       if (field_op == FIELD_OP_NONE)
+               return parse_atom(hist_data, file, str, &flags, var_name);
+
+       if (field_op == FIELD_OP_UNARY_MINUS)
+               return parse_unary(hist_data, file, str, flags, var_name, ++level);
+
+       switch (field_op) {
+       case FIELD_OP_MINUS:
+               sep = "-";
+               break;
+       case FIELD_OP_PLUS:
+               sep = "+";
+               break;
+       default:
+               goto free;
+       }
+
+       operand1_str = strsep(&str, sep);
+       if (!operand1_str || !str)
+               goto free;
+
+       operand_flags = 0;
+       operand1 = parse_atom(hist_data, file, operand1_str,
+                             &operand_flags, NULL);
+       if (IS_ERR(operand1)) {
+               ret = PTR_ERR(operand1);
+               operand1 = NULL;
+               goto free;
+       }
+
+       // rest of string could be another expression e.g. b+c in a+b+c
+       operand_flags = 0;
+       operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, ++level);
+       if (IS_ERR(operand2)) {
+               ret = PTR_ERR(operand2);
+               operand2 = NULL;
+               goto free;
+       }
+
+       ret = check_expr_operands(operand1, operand2);
+       if (ret)
+               goto free;
+
+       flags |= HIST_FIELD_FL_EXPR;
+
+       flags |= operand1->flags &
+               (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
+
+       expr = create_hist_field(hist_data, NULL, flags, var_name);
+       if (!expr) {
+               ret = -ENOMEM;
+               goto free;
+       }
+
+       operand1->read_once = true;
+       operand2->read_once = true;
+
+       expr->operands[0] = operand1;
+       expr->operands[1] = operand2;
+       expr->operator = field_op;
+       expr->name = expr_str(expr, 0);
+       expr->type = kstrdup(operand1->type, GFP_KERNEL);
+       if (!expr->type) {
+               ret = -ENOMEM;
+               goto free;
+       }
+
+       switch (field_op) {
+       case FIELD_OP_MINUS:
+               expr->fn = hist_field_minus;
+               break;
+       case FIELD_OP_PLUS:
+               expr->fn = hist_field_plus;
+               break;
+       default:
+               ret = -EINVAL;
+               goto free;
+       }
+
+       return expr;
+ free:
+       destroy_hist_field(operand1, 0);
+       destroy_hist_field(operand2, 0);
+       destroy_hist_field(expr, 0);
+
+       return ERR_PTR(ret);
+}
+
+static char *find_trigger_filter(struct hist_trigger_data *hist_data,
+                                struct trace_event_file *file)
+{
+       struct event_trigger_data *test;
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       if (test->private_data == hist_data)
+                               return test->filter_str;
+               }
+       }
+
+       return NULL;
+}
+
+static struct event_command trigger_hist_cmd;
+static int event_hist_trigger_func(struct event_command *cmd_ops,
+                                  struct trace_event_file *file,
+                                  char *glob, char *cmd, char *param);
+
+static bool compatible_keys(struct hist_trigger_data *target_hist_data,
+                           struct hist_trigger_data *hist_data,
+                           unsigned int n_keys)
+{
+       struct hist_field *target_hist_field, *hist_field;
+       unsigned int n, i, j;
+
+       if (hist_data->n_fields - hist_data->n_vals != n_keys)
+               return false;
+
+       i = hist_data->n_vals;
+       j = target_hist_data->n_vals;
+
+       for (n = 0; n < n_keys; n++) {
+               hist_field = hist_data->fields[i + n];
+               target_hist_field = target_hist_data->fields[j + n];
+
+               if (strcmp(hist_field->type, target_hist_field->type) != 0)
+                       return false;
+               if (hist_field->size != target_hist_field->size)
+                       return false;
+               if (hist_field->is_signed != target_hist_field->is_signed)
+                       return false;
+       }
+
+       return true;
+}
+
+static struct hist_trigger_data *
+find_compatible_hist(struct hist_trigger_data *target_hist_data,
+                    struct trace_event_file *file)
+{
+       struct hist_trigger_data *hist_data;
+       struct event_trigger_data *test;
+       unsigned int n_keys;
+
+       n_keys = target_hist_data->n_fields - target_hist_data->n_vals;
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       hist_data = test->private_data;
+
+                       if (compatible_keys(target_hist_data, hist_data, n_keys))
+                               return hist_data;
+               }
+       }
+
+       return NULL;
+}
+
+static struct trace_event_file *event_file(struct trace_array *tr,
+                                          char *system, char *event_name)
+{
+       struct trace_event_file *file;
+
+       file = find_event_file(tr, system, event_name);
+       if (!file)
+               return ERR_PTR(-EINVAL);
+
+       return file;
+}
+
+static struct hist_field *
+find_synthetic_field_var(struct hist_trigger_data *target_hist_data,
+                        char *system, char *event_name, char *field_name)
+{
+       struct hist_field *event_var;
+       char *synthetic_name;
+
+       synthetic_name = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL);
+       if (!synthetic_name)
+               return ERR_PTR(-ENOMEM);
+
+       strcpy(synthetic_name, "synthetic_");
+       strcat(synthetic_name, field_name);
+
+       event_var = find_event_var(target_hist_data, system, event_name, synthetic_name);
+
+       kfree(synthetic_name);
+
+       return event_var;
+}
+
+/**
+ * create_field_var_hist - Automatically create a histogram and var for a field
+ * @target_hist_data: The target hist trigger
+ * @subsys_name: Optional subsystem name
+ * @event_name: Optional event name
+ * @field_name: The name of the field (and the resulting variable)
+ *
+ * Hist trigger actions fetch data from variables, not directly from
+ * events.  However, for convenience, users are allowed to directly
+ * specify an event field in an action, which will be automatically
+ * converted into a variable on their behalf.
+
+ * If a user specifies a field on an event that isn't the event the
+ * histogram currently being defined (the target event histogram), the
+ * only way that can be accomplished is if a new hist trigger is
+ * created and the field variable defined on that.
+ *
+ * This function creates a new histogram compatible with the target
+ * event (meaning a histogram with the same key as the target
+ * histogram), and creates a variable for the specified field, but
+ * with 'synthetic_' prepended to the variable name in order to avoid
+ * collision with normal field variables.
+ *
+ * Return: The variable created for the field.
+ */
+static struct hist_field *
+create_field_var_hist(struct hist_trigger_data *target_hist_data,
+                     char *subsys_name, char *event_name, char *field_name)
+{
+       struct trace_array *tr = target_hist_data->event_file->tr;
+       struct hist_field *event_var = ERR_PTR(-EINVAL);
+       struct hist_trigger_data *hist_data;
+       unsigned int i, n, first = true;
+       struct field_var_hist *var_hist;
+       struct trace_event_file *file;
+       struct hist_field *key_field;
+       char *saved_filter;
+       char *cmd;
+       int ret;
+
+       if (target_hist_data->n_field_var_hists >= SYNTH_FIELDS_MAX) {
+               hist_err_event("onmatch: Too many field variables defined: ",
+                              subsys_name, event_name, field_name);
+               return ERR_PTR(-EINVAL);
+       }
+
+       file = event_file(tr, subsys_name, event_name);
+
+       if (IS_ERR(file)) {
+               hist_err_event("onmatch: Event file not found: ",
+                              subsys_name, event_name, field_name);
+               ret = PTR_ERR(file);
+               return ERR_PTR(ret);
+       }
+
+       /*
+        * Look for a histogram compatible with target.  We'll use the
+        * found histogram specification to create a new matching
+        * histogram with our variable on it.  target_hist_data is not
+        * yet a registered histogram so we can't use that.
+        */
+       hist_data = find_compatible_hist(target_hist_data, file);
+       if (!hist_data) {
+               hist_err_event("onmatch: Matching event histogram not found: ",
+                              subsys_name, event_name, field_name);
+               return ERR_PTR(-EINVAL);
+       }
+
+       /* See if a synthetic field variable has already been created */
+       event_var = find_synthetic_field_var(target_hist_data, subsys_name,
+                                            event_name, field_name);
+       if (!IS_ERR_OR_NULL(event_var))
+               return event_var;
+
+       var_hist = kzalloc(sizeof(*var_hist), GFP_KERNEL);
+       if (!var_hist)
+               return ERR_PTR(-ENOMEM);
+
+       cmd = kzalloc(MAX_FILTER_STR_VAL, GFP_KERNEL);
+       if (!cmd) {
+               kfree(var_hist);
+               return ERR_PTR(-ENOMEM);
+       }
+
+       /* Use the same keys as the compatible histogram */
+       strcat(cmd, "keys=");
+
+       for_each_hist_key_field(i, hist_data) {
+               key_field = hist_data->fields[i];
+               if (!first)
+                       strcat(cmd, ",");
+               strcat(cmd, key_field->field->name);
+               first = false;
+       }
+
+       /* Create the synthetic field variable specification */
+       strcat(cmd, ":synthetic_");
+       strcat(cmd, field_name);
+       strcat(cmd, "=");
+       strcat(cmd, field_name);
+
+       /* Use the same filter as the compatible histogram */
+       saved_filter = find_trigger_filter(hist_data, file);
+       if (saved_filter) {
+               strcat(cmd, " if ");
+               strcat(cmd, saved_filter);
+       }
+
+       var_hist->cmd = kstrdup(cmd, GFP_KERNEL);
+       if (!var_hist->cmd) {
+               kfree(cmd);
+               kfree(var_hist);
+               return ERR_PTR(-ENOMEM);
+       }
+
+       /* Save the compatible histogram information */
+       var_hist->hist_data = hist_data;
+
+       /* Create the new histogram with our variable */
+       ret = event_hist_trigger_func(&trigger_hist_cmd, file,
+                                     "", "hist", cmd);
+       if (ret) {
+               kfree(cmd);
+               kfree(var_hist->cmd);
+               kfree(var_hist);
+               hist_err_event("onmatch: Couldn't create histogram for field: ",
+                              subsys_name, event_name, field_name);
+               return ERR_PTR(ret);
+       }
+
+       kfree(cmd);
+
+       /* If we can't find the variable, something went wrong */
+       event_var = find_synthetic_field_var(target_hist_data, subsys_name,
+                                            event_name, field_name);
+       if (IS_ERR_OR_NULL(event_var)) {
+               kfree(var_hist->cmd);
+               kfree(var_hist);
+               hist_err_event("onmatch: Couldn't find synthetic variable: ",
+                              subsys_name, event_name, field_name);
+               return ERR_PTR(-EINVAL);
+       }
+
+       n = target_hist_data->n_field_var_hists;
+       target_hist_data->field_var_hists[n] = var_hist;
+       target_hist_data->n_field_var_hists++;
+
+       return event_var;
+}
+
+static struct hist_field *
+find_target_event_var(struct hist_trigger_data *hist_data,
+                     char *subsys_name, char *event_name, char *var_name)
+{
+       struct trace_event_file *file = hist_data->event_file;
+       struct hist_field *hist_field = NULL;
+
+       if (subsys_name) {
+               struct trace_event_call *call;
+
+               if (!event_name)
+                       return NULL;
+
+               call = file->event_call;
+
+               if (strcmp(subsys_name, call->class->system) != 0)
+                       return NULL;
+
+               if (strcmp(event_name, trace_event_name(call)) != 0)
+                       return NULL;
+       }
+
+       hist_field = find_var_field(hist_data, var_name);
+
+       return hist_field;
+}
+
+static inline void __update_field_vars(struct tracing_map_elt *elt,
+                                      struct ring_buffer_event *rbe,
+                                      void *rec,
+                                      struct field_var **field_vars,
+                                      unsigned int n_field_vars,
+                                      unsigned int field_var_str_start)
+{
+       struct hist_elt_data *elt_data = elt->private_data;
+       unsigned int i, j, var_idx;
+       u64 var_val;
+
+       for (i = 0, j = field_var_str_start; i < n_field_vars; i++) {
+               struct field_var *field_var = field_vars[i];
+               struct hist_field *var = field_var->var;
+               struct hist_field *val = field_var->val;
+
+               var_val = val->fn(val, elt, rbe, rec);
+               var_idx = var->var.idx;
+
+               if (val->flags & HIST_FIELD_FL_STRING) {
+                       char *str = elt_data->field_var_str[j++];
+                       char *val_str = (char *)(uintptr_t)var_val;
+
+                       strscpy(str, val_str, STR_VAR_LEN_MAX);
+                       var_val = (u64)(uintptr_t)str;
+               }
+               tracing_map_set_var(elt, var_idx, var_val);
+       }
+}
+
+static void update_field_vars(struct hist_trigger_data *hist_data,
+                             struct tracing_map_elt *elt,
+                             struct ring_buffer_event *rbe,
+                             void *rec)
+{
+       __update_field_vars(elt, rbe, rec, hist_data->field_vars,
+                           hist_data->n_field_vars, 0);
+}
+
+static void update_max_vars(struct hist_trigger_data *hist_data,
+                           struct tracing_map_elt *elt,
+                           struct ring_buffer_event *rbe,
+                           void *rec)
+{
+       __update_field_vars(elt, rbe, rec, hist_data->max_vars,
+                           hist_data->n_max_vars, hist_data->n_field_var_str);
+}
+
+static struct hist_field *create_var(struct hist_trigger_data *hist_data,
+                                    struct trace_event_file *file,
+                                    char *name, int size, const char *type)
+{
+       struct hist_field *var;
+       int idx;
+
+       if (find_var(hist_data, file, name) && !hist_data->remove) {
+               var = ERR_PTR(-EINVAL);
+               goto out;
+       }
+
+       var = kzalloc(sizeof(struct hist_field), GFP_KERNEL);
+       if (!var) {
+               var = ERR_PTR(-ENOMEM);
+               goto out;
+       }
+
+       idx = tracing_map_add_var(hist_data->map);
+       if (idx < 0) {
+               kfree(var);
+               var = ERR_PTR(-EINVAL);
+               goto out;
+       }
+
+       var->flags = HIST_FIELD_FL_VAR;
+       var->var.idx = idx;
+       var->var.hist_data = var->hist_data = hist_data;
+       var->size = size;
+       var->var.name = kstrdup(name, GFP_KERNEL);
+       var->type = kstrdup(type, GFP_KERNEL);
+       if (!var->var.name || !var->type) {
+               kfree(var->var.name);
+               kfree(var->type);
+               kfree(var);
+               var = ERR_PTR(-ENOMEM);
+       }
+ out:
+       return var;
+}
+
+static struct field_var *create_field_var(struct hist_trigger_data *hist_data,
+                                         struct trace_event_file *file,
+                                         char *field_name)
+{
+       struct hist_field *val = NULL, *var = NULL;
+       unsigned long flags = HIST_FIELD_FL_VAR;
+       struct field_var *field_var;
+       int ret = 0;
+
+       if (hist_data->n_field_vars >= SYNTH_FIELDS_MAX) {
+               hist_err("Too many field variables defined: ", field_name);
+               ret = -EINVAL;
+               goto err;
+       }
+
+       val = parse_atom(hist_data, file, field_name, &flags, NULL);
+       if (IS_ERR(val)) {
+               hist_err("Couldn't parse field variable: ", field_name);
+               ret = PTR_ERR(val);
+               goto err;
+       }
+
+       var = create_var(hist_data, file, field_name, val->size, val->type);
+       if (IS_ERR(var)) {
+               hist_err("Couldn't create or find variable: ", field_name);
+               kfree(val);
+               ret = PTR_ERR(var);
+               goto err;
+       }
+
+       field_var = kzalloc(sizeof(struct field_var), GFP_KERNEL);
+       if (!field_var) {
+               kfree(val);
+               kfree(var);
+               ret =  -ENOMEM;
+               goto err;
+       }
+
+       field_var->var = var;
+       field_var->val = val;
+ out:
+       return field_var;
+ err:
+       field_var = ERR_PTR(ret);
+       goto out;
+}
+
+/**
+ * create_target_field_var - Automatically create a variable for a field
+ * @target_hist_data: The target hist trigger
+ * @subsys_name: Optional subsystem name
+ * @event_name: Optional event name
+ * @var_name: The name of the field (and the resulting variable)
+ *
+ * Hist trigger actions fetch data from variables, not directly from
+ * events.  However, for convenience, users are allowed to directly
+ * specify an event field in an action, which will be automatically
+ * converted into a variable on their behalf.
+
+ * This function creates a field variable with the name var_name on
+ * the hist trigger currently being defined on the target event.  If
+ * subsys_name and event_name are specified, this function simply
+ * verifies that they do in fact match the target event subsystem and
+ * event name.
+ *
+ * Return: The variable created for the field.
+ */
+static struct field_var *
+create_target_field_var(struct hist_trigger_data *target_hist_data,
+                       char *subsys_name, char *event_name, char *var_name)
+{
+       struct trace_event_file *file = target_hist_data->event_file;
+
+       if (subsys_name) {
+               struct trace_event_call *call;
+
+               if (!event_name)
+                       return NULL;
+
+               call = file->event_call;
+
+               if (strcmp(subsys_name, call->class->system) != 0)
+                       return NULL;
+
+               if (strcmp(event_name, trace_event_name(call)) != 0)
+                       return NULL;
+       }
+
+       return create_field_var(target_hist_data, file, var_name);
+}
+
+static void onmax_print(struct seq_file *m,
+                       struct hist_trigger_data *hist_data,
+                       struct tracing_map_elt *elt,
+                       struct action_data *data)
+{
+       unsigned int i, save_var_idx, max_idx = data->onmax.max_var->var.idx;
+
+       seq_printf(m, "\n\tmax: %10llu", tracing_map_read_var(elt, max_idx));
+
+       for (i = 0; i < hist_data->n_max_vars; i++) {
+               struct hist_field *save_val = hist_data->max_vars[i]->val;
+               struct hist_field *save_var = hist_data->max_vars[i]->var;
+               u64 val;
+
+               save_var_idx = save_var->var.idx;
+
+               val = tracing_map_read_var(elt, save_var_idx);
+
+               if (save_val->flags & HIST_FIELD_FL_STRING) {
+                       seq_printf(m, "  %s: %-32s", save_var->var.name,
+                                  (char *)(uintptr_t)(val));
+               } else
+                       seq_printf(m, "  %s: %10llu", save_var->var.name, val);
+       }
+}
+
+static void onmax_save(struct hist_trigger_data *hist_data,
+                      struct tracing_map_elt *elt, void *rec,
+                      struct ring_buffer_event *rbe,
+                      struct action_data *data, u64 *var_ref_vals)
+{
+       unsigned int max_idx = data->onmax.max_var->var.idx;
+       unsigned int max_var_ref_idx = data->onmax.max_var_ref_idx;
+
+       u64 var_val, max_val;
+
+       var_val = var_ref_vals[max_var_ref_idx];
+       max_val = tracing_map_read_var(elt, max_idx);
+
+       if (var_val <= max_val)
+               return;
+
+       tracing_map_set_var(elt, max_idx, var_val);
+
+       update_max_vars(hist_data, elt, rbe, rec);
+}
+
+static void onmax_destroy(struct action_data *data)
+{
+       unsigned int i;
+
+       destroy_hist_field(data->onmax.max_var, 0);
+       destroy_hist_field(data->onmax.var, 0);
+
+       kfree(data->onmax.var_str);
+       kfree(data->onmax.fn_name);
+
+       for (i = 0; i < data->n_params; i++)
+               kfree(data->params[i]);
+
+       kfree(data);
+}
+
+static int onmax_create(struct hist_trigger_data *hist_data,
+                       struct action_data *data)
+{
+       struct trace_event_file *file = hist_data->event_file;
+       struct hist_field *var_field, *ref_field, *max_var;
+       unsigned int var_ref_idx = hist_data->n_var_refs;
+       struct field_var *field_var;
+       char *onmax_var_str, *param;
+       unsigned long flags;
+       unsigned int i;
+       int ret = 0;
+
+       onmax_var_str = data->onmax.var_str;
+       if (onmax_var_str[0] != '$') {
+               hist_err("onmax: For onmax(x), x must be a variable: ", onmax_var_str);
+               return -EINVAL;
+       }
+       onmax_var_str++;
+
+       var_field = find_target_event_var(hist_data, NULL, NULL, onmax_var_str);
+       if (!var_field) {
+               hist_err("onmax: Couldn't find onmax variable: ", onmax_var_str);
+               return -EINVAL;
+       }
+
+       flags = HIST_FIELD_FL_VAR_REF;
+       ref_field = create_hist_field(hist_data, NULL, flags, NULL);
+       if (!ref_field)
+               return -ENOMEM;
+
+       if (init_var_ref(ref_field, var_field, NULL, NULL)) {
+               destroy_hist_field(ref_field, 0);
+               ret = -ENOMEM;
+               goto out;
+       }
+       hist_data->var_refs[hist_data->n_var_refs] = ref_field;
+       ref_field->var_ref_idx = hist_data->n_var_refs++;
+       data->onmax.var = ref_field;
+
+       data->fn = onmax_save;
+       data->onmax.max_var_ref_idx = var_ref_idx;
+       max_var = create_var(hist_data, file, "max", sizeof(u64), "u64");
+       if (IS_ERR(max_var)) {
+               hist_err("onmax: Couldn't create onmax variable: ", "max");
+               ret = PTR_ERR(max_var);
+               goto out;
+       }
+       data->onmax.max_var = max_var;
+
+       for (i = 0; i < data->n_params; i++) {
+               param = kstrdup(data->params[i], GFP_KERNEL);
+               if (!param) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+
+               field_var = create_target_field_var(hist_data, NULL, NULL, param);
+               if (IS_ERR(field_var)) {
+                       hist_err("onmax: Couldn't create field variable: ", param);
+                       ret = PTR_ERR(field_var);
+                       kfree(param);
+                       goto out;
+               }
+
+               hist_data->max_vars[hist_data->n_max_vars++] = field_var;
+               if (field_var->val->flags & HIST_FIELD_FL_STRING)
+                       hist_data->n_max_var_str++;
+
+               kfree(param);
+       }
+ out:
+       return ret;
+}
+
+static int parse_action_params(char *params, struct action_data *data)
+{
+       char *param, *saved_param;
+       int ret = 0;
+
+       while (params) {
+               if (data->n_params >= SYNTH_FIELDS_MAX)
+                       goto out;
+
+               param = strsep(&params, ",");
+               if (!param) {
+                       ret = -EINVAL;
+                       goto out;
+               }
+
+               param = strstrip(param);
+               if (strlen(param) < 2) {
+                       hist_err("Invalid action param: ", param);
+                       ret = -EINVAL;
+                       goto out;
+               }
+
+               saved_param = kstrdup(param, GFP_KERNEL);
+               if (!saved_param) {
+                       ret = -ENOMEM;
+                       goto out;
+               }
+
+               data->params[data->n_params++] = saved_param;
+       }
+ out:
+       return ret;
+}
+
+static struct action_data *onmax_parse(char *str)
+{
+       char *onmax_fn_name, *onmax_var_str;
+       struct action_data *data;
+       int ret = -EINVAL;
+
+       data = kzalloc(sizeof(*data), GFP_KERNEL);
+       if (!data)
+               return ERR_PTR(-ENOMEM);
+
+       onmax_var_str = strsep(&str, ")");
+       if (!onmax_var_str || !str) {
+               ret = -EINVAL;
+               goto free;
+       }
+
+       data->onmax.var_str = kstrdup(onmax_var_str, GFP_KERNEL);
+       if (!data->onmax.var_str) {
+               ret = -ENOMEM;
+               goto free;
+       }
+
+       strsep(&str, ".");
+       if (!str)
+               goto free;
+
+       onmax_fn_name = strsep(&str, "(");
+       if (!onmax_fn_name || !str)
+               goto free;
+
+       if (strncmp(onmax_fn_name, "save", strlen("save")) == 0) {
+               char *params = strsep(&str, ")");
+
+               if (!params) {
+                       ret = -EINVAL;
+                       goto free;
+               }
+
+               ret = parse_action_params(params, data);
+               if (ret)
+                       goto free;
+       } else
+               goto free;
+
+       data->onmax.fn_name = kstrdup(onmax_fn_name, GFP_KERNEL);
+       if (!data->onmax.fn_name) {
+               ret = -ENOMEM;
+               goto free;
+       }
+ out:
+       return data;
+ free:
+       onmax_destroy(data);
+       data = ERR_PTR(ret);
+       goto out;
+}
+
+static void onmatch_destroy(struct action_data *data)
+{
+       unsigned int i;
+
+       mutex_lock(&synth_event_mutex);
+
+       kfree(data->onmatch.match_event);
+       kfree(data->onmatch.match_event_system);
+       kfree(data->onmatch.synth_event_name);
+
+       for (i = 0; i < data->n_params; i++)
+               kfree(data->params[i]);
+
+       if (data->onmatch.synth_event)
+               data->onmatch.synth_event->ref--;
+
+       kfree(data);
+
+       mutex_unlock(&synth_event_mutex);
+}
+
+static void destroy_field_var(struct field_var *field_var)
+{
+       if (!field_var)
+               return;
+
+       destroy_hist_field(field_var->var, 0);
+       destroy_hist_field(field_var->val, 0);
+
+       kfree(field_var);
+}
+
+static void destroy_field_vars(struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_field_vars; i++)
+               destroy_field_var(hist_data->field_vars[i]);
+}
+
+static void save_field_var(struct hist_trigger_data *hist_data,
+                          struct field_var *field_var)
+{
+       hist_data->field_vars[hist_data->n_field_vars++] = field_var;
+
+       if (field_var->val->flags & HIST_FIELD_FL_STRING)
+               hist_data->n_field_var_str++;
+}
+
+
+static void destroy_synth_var_refs(struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_synth_var_refs; i++)
+               destroy_hist_field(hist_data->synth_var_refs[i], 0);
+}
+
+static void save_synth_var_ref(struct hist_trigger_data *hist_data,
+                        struct hist_field *var_ref)
+{
+       hist_data->synth_var_refs[hist_data->n_synth_var_refs++] = var_ref;
+
+       hist_data->var_refs[hist_data->n_var_refs] = var_ref;
+       var_ref->var_ref_idx = hist_data->n_var_refs++;
+}
+
+static int check_synth_field(struct synth_event *event,
+                            struct hist_field *hist_field,
+                            unsigned int field_pos)
+{
+       struct synth_field *field;
+
+       if (field_pos >= event->n_fields)
+               return -EINVAL;
+
+       field = event->fields[field_pos];
+
+       if (strcmp(field->type, hist_field->type) != 0)
+               return -EINVAL;
+
+       return 0;
+}
+
+static struct hist_field *
+onmatch_find_var(struct hist_trigger_data *hist_data, struct action_data *data,
+                char *system, char *event, char *var)
+{
+       struct hist_field *hist_field;
+
+       var++; /* skip '$' */
+
+       hist_field = find_target_event_var(hist_data, system, event, var);
+       if (!hist_field) {
+               if (!system) {
+                       system = data->onmatch.match_event_system;
+                       event = data->onmatch.match_event;
+               }
+
+               hist_field = find_event_var(hist_data, system, event, var);
+       }
+
+       if (!hist_field)
+               hist_err_event("onmatch: Couldn't find onmatch param: $", system, event, var);
+
+       return hist_field;
+}
+
+static struct hist_field *
+onmatch_create_field_var(struct hist_trigger_data *hist_data,
+                        struct action_data *data, char *system,
+                        char *event, char *var)
+{
+       struct hist_field *hist_field = NULL;
+       struct field_var *field_var;
+
+       /*
+        * First try to create a field var on the target event (the
+        * currently being defined).  This will create a variable for
+        * unqualified fields on the target event, or if qualified,
+        * target fields that have qualified names matching the target.
+        */
+       field_var = create_target_field_var(hist_data, system, event, var);
+
+       if (field_var && !IS_ERR(field_var)) {
+               save_field_var(hist_data, field_var);
+               hist_field = field_var->var;
+       } else {
+               field_var = NULL;
+               /*
+                * If no explicit system.event is specfied, default to
+                * looking for fields on the onmatch(system.event.xxx)
+                * event.
+                */
+               if (!system) {
+                       system = data->onmatch.match_event_system;
+                       event = data->onmatch.match_event;
+               }
+
+               /*
+                * At this point, we're looking at a field on another
+                * event.  Because we can't modify a hist trigger on
+                * another event to add a variable for a field, we need
+                * to create a new trigger on that event and create the
+                * variable at the same time.
+                */
+               hist_field = create_field_var_hist(hist_data, system, event, var);
+               if (IS_ERR(hist_field))
+                       goto free;
+       }
+ out:
+       return hist_field;
+ free:
+       destroy_field_var(field_var);
+       hist_field = NULL;
+       goto out;
+}
+
+static int onmatch_create(struct hist_trigger_data *hist_data,
+                         struct trace_event_file *file,
+                         struct action_data *data)
+{
+       char *event_name, *param, *system = NULL;
+       struct hist_field *hist_field, *var_ref;
+       unsigned int i, var_ref_idx;
+       unsigned int field_pos = 0;
+       struct synth_event *event;
+       int ret = 0;
+
+       mutex_lock(&synth_event_mutex);
+       event = find_synth_event(data->onmatch.synth_event_name);
+       if (!event) {
+               hist_err("onmatch: Couldn't find synthetic event: ", data->onmatch.synth_event_name);
+               mutex_unlock(&synth_event_mutex);
+               return -EINVAL;
+       }
+       event->ref++;
+       mutex_unlock(&synth_event_mutex);
+
+       var_ref_idx = hist_data->n_var_refs;
+
+       for (i = 0; i < data->n_params; i++) {
+               char *p;
+
+               p = param = kstrdup(data->params[i], GFP_KERNEL);
+               if (!param) {
+                       ret = -ENOMEM;
+                       goto err;
+               }
+
+               system = strsep(&param, ".");
+               if (!param) {
+                       param = (char *)system;
+                       system = event_name = NULL;
+               } else {
+                       event_name = strsep(&param, ".");
+                       if (!param) {
+                               kfree(p);
+                               ret = -EINVAL;
+                               goto err;
+                       }
+               }
+
+               if (param[0] == '$')
+                       hist_field = onmatch_find_var(hist_data, data, system,
+                                                     event_name, param);
+               else
+                       hist_field = onmatch_create_field_var(hist_data, data,
+                                                             system,
+                                                             event_name,
+                                                             param);
+
+               if (!hist_field) {
+                       kfree(p);
+                       ret = -EINVAL;
+                       goto err;
+               }
+
+               if (check_synth_field(event, hist_field, field_pos) == 0) {
+                       var_ref = create_var_ref(hist_field, system, event_name);
+                       if (!var_ref) {
+                               kfree(p);
+                               ret = -ENOMEM;
+                               goto err;
+                       }
+
+                       save_synth_var_ref(hist_data, var_ref);
+                       field_pos++;
+                       kfree(p);
+                       continue;
+               }
+
+               hist_err_event("onmatch: Param type doesn't match synthetic event field type: ",
+                              system, event_name, param);
+               kfree(p);
+               ret = -EINVAL;
+               goto err;
+       }
+
+       if (field_pos != event->n_fields) {
+               hist_err("onmatch: Param count doesn't match synthetic event field count: ", event->name);
+               ret = -EINVAL;
+               goto err;
+       }
+
+       data->fn = action_trace;
+       data->onmatch.synth_event = event;
+       data->onmatch.var_ref_idx = var_ref_idx;
+ out:
+       return ret;
+ err:
+       mutex_lock(&synth_event_mutex);
+       event->ref--;
+       mutex_unlock(&synth_event_mutex);
+
+       goto out;
+}
+
+static struct action_data *onmatch_parse(struct trace_array *tr, char *str)
+{
+       char *match_event, *match_event_system;
+       char *synth_event_name, *params;
+       struct action_data *data;
+       int ret = -EINVAL;
+
+       data = kzalloc(sizeof(*data), GFP_KERNEL);
+       if (!data)
+               return ERR_PTR(-ENOMEM);
+
+       match_event = strsep(&str, ")");
+       if (!match_event || !str) {
+               hist_err("onmatch: Missing closing paren: ", match_event);
+               goto free;
+       }
+
+       match_event_system = strsep(&match_event, ".");
+       if (!match_event) {
+               hist_err("onmatch: Missing subsystem for match event: ", match_event_system);
+               goto free;
+       }
+
+       if (IS_ERR(event_file(tr, match_event_system, match_event))) {
+               hist_err_event("onmatch: Invalid subsystem or event name: ",
+                              match_event_system, match_event, NULL);
+               goto free;
        }
 
-       if (WARN_ON_ONCE(!field))
-               goto out;
+       data->onmatch.match_event = kstrdup(match_event, GFP_KERNEL);
+       if (!data->onmatch.match_event) {
+               ret = -ENOMEM;
+               goto free;
+       }
 
-       if (is_string_field(field)) {
-               flags |= HIST_FIELD_FL_STRING;
+       data->onmatch.match_event_system = kstrdup(match_event_system, GFP_KERNEL);
+       if (!data->onmatch.match_event_system) {
+               ret = -ENOMEM;
+               goto free;
+       }
 
-               if (field->filter_type == FILTER_STATIC_STRING)
-                       hist_field->fn = hist_field_string;
-               else if (field->filter_type == FILTER_DYN_STRING)
-                       hist_field->fn = hist_field_dynstring;
-               else
-                       hist_field->fn = hist_field_pstring;
-       } else {
-               hist_field->fn = select_value_fn(field->size,
-                                                field->is_signed);
-               if (!hist_field->fn) {
-                       destroy_hist_field(hist_field);
-                       return NULL;
-               }
+       strsep(&str, ".");
+       if (!str) {
+               hist_err("onmatch: Missing . after onmatch(): ", str);
+               goto free;
        }
- out:
-       hist_field->field = field;
-       hist_field->flags = flags;
 
-       return hist_field;
-}
+       synth_event_name = strsep(&str, "(");
+       if (!synth_event_name || !str) {
+               hist_err("onmatch: Missing opening paramlist paren: ", synth_event_name);
+               goto free;
+       }
 
-static void destroy_hist_fields(struct hist_trigger_data *hist_data)
-{
-       unsigned int i;
+       data->onmatch.synth_event_name = kstrdup(synth_event_name, GFP_KERNEL);
+       if (!data->onmatch.synth_event_name) {
+               ret = -ENOMEM;
+               goto free;
+       }
 
-       for (i = 0; i < TRACING_MAP_FIELDS_MAX; i++) {
-               if (hist_data->fields[i]) {
-                       destroy_hist_field(hist_data->fields[i]);
-                       hist_data->fields[i] = NULL;
-               }
+       params = strsep(&str, ")");
+       if (!params || !str || (str && strlen(str))) {
+               hist_err("onmatch: Missing closing paramlist paren: ", params);
+               goto free;
        }
+
+       ret = parse_action_params(params, data);
+       if (ret)
+               goto free;
+ out:
+       return data;
+ free:
+       onmatch_destroy(data);
+       data = ERR_PTR(ret);
+       goto out;
 }
 
 static int create_hitcount_val(struct hist_trigger_data *hist_data)
 {
        hist_data->fields[HITCOUNT_IDX] =
-               create_hist_field(NULL, HIST_FIELD_FL_HITCOUNT);
+               create_hist_field(hist_data, NULL, HIST_FIELD_FL_HITCOUNT, NULL);
        if (!hist_data->fields[HITCOUNT_IDX])
                return -ENOMEM;
 
        hist_data->n_vals++;
+       hist_data->n_fields++;
 
        if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX))
                return -EINVAL;
@@ -426,54 +3828,71 @@ static int create_hitcount_val(struct hist_trigger_data *hist_data)
        return 0;
 }
 
+static int __create_val_field(struct hist_trigger_data *hist_data,
+                             unsigned int val_idx,
+                             struct trace_event_file *file,
+                             char *var_name, char *field_str,
+                             unsigned long flags)
+{
+       struct hist_field *hist_field;
+       int ret = 0;
+
+       hist_field = parse_expr(hist_data, file, field_str, flags, var_name, 0);
+       if (IS_ERR(hist_field)) {
+               ret = PTR_ERR(hist_field);
+               goto out;
+       }
+
+       hist_data->fields[val_idx] = hist_field;
+
+       ++hist_data->n_vals;
+       ++hist_data->n_fields;
+
+       if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX))
+               ret = -EINVAL;
+ out:
+       return ret;
+}
+
 static int create_val_field(struct hist_trigger_data *hist_data,
                            unsigned int val_idx,
                            struct trace_event_file *file,
                            char *field_str)
 {
-       struct ftrace_event_field *field = NULL;
-       unsigned long flags = 0;
-       char *field_name;
-       int ret = 0;
-
        if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX))
                return -EINVAL;
 
-       field_name = strsep(&field_str, ".");
-       if (field_str) {
-               if (strcmp(field_str, "hex") == 0)
-                       flags |= HIST_FIELD_FL_HEX;
-               else {
-                       ret = -EINVAL;
-                       goto out;
-               }
-       }
+       return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0);
+}
 
-       field = trace_find_event_field(file->event_call, field_name);
-       if (!field || !field->size) {
-               ret = -EINVAL;
-               goto out;
-       }
+static int create_var_field(struct hist_trigger_data *hist_data,
+                           unsigned int val_idx,
+                           struct trace_event_file *file,
+                           char *var_name, char *expr_str)
+{
+       unsigned long flags = 0;
 
-       hist_data->fields[val_idx] = create_hist_field(field, flags);
-       if (!hist_data->fields[val_idx]) {
-               ret = -ENOMEM;
-               goto out;
+       if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX))
+               return -EINVAL;
+
+       if (find_var(hist_data, file, var_name) && !hist_data->remove) {
+               hist_err("Variable already defined: ", var_name);
+               return -EINVAL;
        }
 
-       ++hist_data->n_vals;
+       flags |= HIST_FIELD_FL_VAR;
+       hist_data->n_vars++;
+       if (WARN_ON(hist_data->n_vars > TRACING_MAP_VARS_MAX))
+               return -EINVAL;
 
-       if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX))
-               ret = -EINVAL;
- out:
-       return ret;
+       return __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags);
 }
 
 static int create_val_fields(struct hist_trigger_data *hist_data,
                             struct trace_event_file *file)
 {
        char *fields_str, *field_str;
-       unsigned int i, j;
+       unsigned int i, j = 1;
        int ret;
 
        ret = create_hitcount_val(hist_data);
@@ -493,12 +3912,15 @@ static int create_val_fields(struct hist_trigger_data *hist_data,
                field_str = strsep(&fields_str, ",");
                if (!field_str)
                        break;
+
                if (strcmp(field_str, "hitcount") == 0)
                        continue;
+
                ret = create_val_field(hist_data, j++, file, field_str);
                if (ret)
                        goto out;
        }
+
        if (fields_str && (strcmp(fields_str, "hitcount") != 0))
                ret = -EINVAL;
  out:
@@ -511,12 +3933,13 @@ static int create_key_field(struct hist_trigger_data *hist_data,
                            struct trace_event_file *file,
                            char *field_str)
 {
-       struct ftrace_event_field *field = NULL;
+       struct hist_field *hist_field = NULL;
+
        unsigned long flags = 0;
        unsigned int key_size;
        int ret = 0;
 
-       if (WARN_ON(key_idx >= TRACING_MAP_FIELDS_MAX))
+       if (WARN_ON(key_idx >= HIST_FIELDS_MAX))
                return -EINVAL;
 
        flags |= HIST_FIELD_FL_KEY;
@@ -524,57 +3947,40 @@ static int create_key_field(struct hist_trigger_data *hist_data,
        if (strcmp(field_str, "stacktrace") == 0) {
                flags |= HIST_FIELD_FL_STACKTRACE;
                key_size = sizeof(unsigned long) * HIST_STACKTRACE_DEPTH;
+               hist_field = create_hist_field(hist_data, NULL, flags, NULL);
        } else {
-               char *field_name = strsep(&field_str, ".");
-
-               if (field_str) {
-                       if (strcmp(field_str, "hex") == 0)
-                               flags |= HIST_FIELD_FL_HEX;
-                       else if (strcmp(field_str, "sym") == 0)
-                               flags |= HIST_FIELD_FL_SYM;
-                       else if (strcmp(field_str, "sym-offset") == 0)
-                               flags |= HIST_FIELD_FL_SYM_OFFSET;
-                       else if ((strcmp(field_str, "execname") == 0) &&
-                                (strcmp(field_name, "common_pid") == 0))
-                               flags |= HIST_FIELD_FL_EXECNAME;
-                       else if (strcmp(field_str, "syscall") == 0)
-                               flags |= HIST_FIELD_FL_SYSCALL;
-                       else if (strcmp(field_str, "log2") == 0)
-                               flags |= HIST_FIELD_FL_LOG2;
-                       else {
-                               ret = -EINVAL;
-                               goto out;
-                       }
+               hist_field = parse_expr(hist_data, file, field_str, flags,
+                                       NULL, 0);
+               if (IS_ERR(hist_field)) {
+                       ret = PTR_ERR(hist_field);
+                       goto out;
                }
 
-               field = trace_find_event_field(file->event_call, field_name);
-               if (!field || !field->size) {
+               if (hist_field->flags & HIST_FIELD_FL_VAR_REF) {
+                       hist_err("Using variable references as keys not supported: ", field_str);
+                       destroy_hist_field(hist_field, 0);
                        ret = -EINVAL;
                        goto out;
                }
 
-               if (is_string_field(field))
-                       key_size = MAX_FILTER_STR_VAL;
-               else
-                       key_size = field->size;
+               key_size = hist_field->size;
        }
 
-       hist_data->fields[key_idx] = create_hist_field(field, flags);
-       if (!hist_data->fields[key_idx]) {
-               ret = -ENOMEM;
-               goto out;
-       }
+       hist_data->fields[key_idx] = hist_field;
 
        key_size = ALIGN(key_size, sizeof(u64));
        hist_data->fields[key_idx]->size = key_size;
        hist_data->fields[key_idx]->offset = key_offset;
+
        hist_data->key_size += key_size;
+
        if (hist_data->key_size > HIST_KEY_SIZE_MAX) {
                ret = -EINVAL;
                goto out;
        }
 
        hist_data->n_keys++;
+       hist_data->n_fields++;
 
        if (WARN_ON(hist_data->n_keys > TRACING_MAP_KEYS_MAX))
                return -EINVAL;
@@ -618,21 +4024,113 @@ static int create_key_fields(struct hist_trigger_data *hist_data,
        return ret;
 }
 
+static int create_var_fields(struct hist_trigger_data *hist_data,
+                            struct trace_event_file *file)
+{
+       unsigned int i, j = hist_data->n_vals;
+       int ret = 0;
+
+       unsigned int n_vars = hist_data->attrs->var_defs.n_vars;
+
+       for (i = 0; i < n_vars; i++) {
+               char *var_name = hist_data->attrs->var_defs.name[i];
+               char *expr = hist_data->attrs->var_defs.expr[i];
+
+               ret = create_var_field(hist_data, j++, file, var_name, expr);
+               if (ret)
+                       goto out;
+       }
+ out:
+       return ret;
+}
+
+static void free_var_defs(struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->attrs->var_defs.n_vars; i++) {
+               kfree(hist_data->attrs->var_defs.name[i]);
+               kfree(hist_data->attrs->var_defs.expr[i]);
+       }
+
+       hist_data->attrs->var_defs.n_vars = 0;
+}
+
+static int parse_var_defs(struct hist_trigger_data *hist_data)
+{
+       char *s, *str, *var_name, *field_str;
+       unsigned int i, j, n_vars = 0;
+       int ret = 0;
+
+       for (i = 0; i < hist_data->attrs->n_assignments; i++) {
+               str = hist_data->attrs->assignment_str[i];
+               for (j = 0; j < TRACING_MAP_VARS_MAX; j++) {
+                       field_str = strsep(&str, ",");
+                       if (!field_str)
+                               break;
+
+                       var_name = strsep(&field_str, "=");
+                       if (!var_name || !field_str) {
+                               hist_err("Malformed assignment: ", var_name);
+                               ret = -EINVAL;
+                               goto free;
+                       }
+
+                       if (n_vars == TRACING_MAP_VARS_MAX) {
+                               hist_err("Too many variables defined: ", var_name);
+                               ret = -EINVAL;
+                               goto free;
+                       }
+
+                       s = kstrdup(var_name, GFP_KERNEL);
+                       if (!s) {
+                               ret = -ENOMEM;
+                               goto free;
+                       }
+                       hist_data->attrs->var_defs.name[n_vars] = s;
+
+                       s = kstrdup(field_str, GFP_KERNEL);
+                       if (!s) {
+                               kfree(hist_data->attrs->var_defs.name[n_vars]);
+                               ret = -ENOMEM;
+                               goto free;
+                       }
+                       hist_data->attrs->var_defs.expr[n_vars++] = s;
+
+                       hist_data->attrs->var_defs.n_vars = n_vars;
+               }
+       }
+
+       return ret;
+ free:
+       free_var_defs(hist_data);
+
+       return ret;
+}
+
 static int create_hist_fields(struct hist_trigger_data *hist_data,
                              struct trace_event_file *file)
 {
        int ret;
 
+       ret = parse_var_defs(hist_data);
+       if (ret)
+               goto out;
+
        ret = create_val_fields(hist_data, file);
        if (ret)
                goto out;
 
-       ret = create_key_fields(hist_data, file);
+       ret = create_var_fields(hist_data, file);
        if (ret)
                goto out;
 
-       hist_data->n_fields = hist_data->n_vals + hist_data->n_keys;
+       ret = create_key_fields(hist_data, file);
+       if (ret)
+               goto out;
  out:
+       free_var_defs(hist_data);
+
        return ret;
 }
 
@@ -653,10 +4151,9 @@ static int is_descending(const char *str)
 static int create_sort_keys(struct hist_trigger_data *hist_data)
 {
        char *fields_str = hist_data->attrs->sort_key_str;
-       struct ftrace_event_field *field = NULL;
        struct tracing_map_sort_key *sort_key;
        int descending, ret = 0;
-       unsigned int i, j;
+       unsigned int i, j, k;
 
        hist_data->n_sort_keys = 1; /* we always have at least one, hitcount */
 
@@ -670,7 +4167,9 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
        }
 
        for (i = 0; i < TRACING_MAP_SORT_KEYS_MAX; i++) {
+               struct hist_field *hist_field;
                char *field_str, *field_name;
+               const char *test_name;
 
                sort_key = &hist_data->sort_keys[i];
 
@@ -702,10 +4201,19 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
                        continue;
                }
 
-               for (j = 1; j < hist_data->n_fields; j++) {
-                       field = hist_data->fields[j]->field;
-                       if (field && (strcmp(field_name, field->name) == 0)) {
-                               sort_key->field_idx = j;
+               for (j = 1, k = 1; j < hist_data->n_fields; j++) {
+                       unsigned int idx;
+
+                       hist_field = hist_data->fields[j];
+                       if (hist_field->flags & HIST_FIELD_FL_VAR)
+                               continue;
+
+                       idx = k++;
+
+                       test_name = hist_field_name(hist_field, 0);
+
+                       if (strcmp(field_name, test_name) == 0) {
+                               sort_key->field_idx = idx;
                                descending = is_descending(field_str);
                                if (descending < 0) {
                                        ret = descending;
@@ -720,16 +4228,230 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
                        break;
                }
        }
-       hist_data->n_sort_keys = i;
- out:
-       return ret;
+
+       hist_data->n_sort_keys = i;
+ out:
+       return ret;
+}
+
+static void destroy_actions(struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_actions; i++) {
+               struct action_data *data = hist_data->actions[i];
+
+               if (data->fn == action_trace)
+                       onmatch_destroy(data);
+               else if (data->fn == onmax_save)
+                       onmax_destroy(data);
+               else
+                       kfree(data);
+       }
+}
+
+static int parse_actions(struct hist_trigger_data *hist_data)
+{
+       struct trace_array *tr = hist_data->event_file->tr;
+       struct action_data *data;
+       unsigned int i;
+       int ret = 0;
+       char *str;
+
+       for (i = 0; i < hist_data->attrs->n_actions; i++) {
+               str = hist_data->attrs->action_str[i];
+
+               if (strncmp(str, "onmatch(", strlen("onmatch(")) == 0) {
+                       char *action_str = str + strlen("onmatch(");
+
+                       data = onmatch_parse(tr, action_str);
+                       if (IS_ERR(data)) {
+                               ret = PTR_ERR(data);
+                               break;
+                       }
+                       data->fn = action_trace;
+               } else if (strncmp(str, "onmax(", strlen("onmax(")) == 0) {
+                       char *action_str = str + strlen("onmax(");
+
+                       data = onmax_parse(action_str);
+                       if (IS_ERR(data)) {
+                               ret = PTR_ERR(data);
+                               break;
+                       }
+                       data->fn = onmax_save;
+               } else {
+                       ret = -EINVAL;
+                       break;
+               }
+
+               hist_data->actions[hist_data->n_actions++] = data;
+       }
+
+       return ret;
+}
+
+static int create_actions(struct hist_trigger_data *hist_data,
+                         struct trace_event_file *file)
+{
+       struct action_data *data;
+       unsigned int i;
+       int ret = 0;
+
+       for (i = 0; i < hist_data->attrs->n_actions; i++) {
+               data = hist_data->actions[i];
+
+               if (data->fn == action_trace) {
+                       ret = onmatch_create(hist_data, file, data);
+                       if (ret)
+                               return ret;
+               } else if (data->fn == onmax_save) {
+                       ret = onmax_create(hist_data, data);
+                       if (ret)
+                               return ret;
+               }
+       }
+
+       return ret;
+}
+
+static void print_actions(struct seq_file *m,
+                         struct hist_trigger_data *hist_data,
+                         struct tracing_map_elt *elt)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_actions; i++) {
+               struct action_data *data = hist_data->actions[i];
+
+               if (data->fn == onmax_save)
+                       onmax_print(m, hist_data, elt, data);
+       }
+}
+
+static void print_onmax_spec(struct seq_file *m,
+                            struct hist_trigger_data *hist_data,
+                            struct action_data *data)
+{
+       unsigned int i;
+
+       seq_puts(m, ":onmax(");
+       seq_printf(m, "%s", data->onmax.var_str);
+       seq_printf(m, ").%s(", data->onmax.fn_name);
+
+       for (i = 0; i < hist_data->n_max_vars; i++) {
+               seq_printf(m, "%s", hist_data->max_vars[i]->var->var.name);
+               if (i < hist_data->n_max_vars - 1)
+                       seq_puts(m, ",");
+       }
+       seq_puts(m, ")");
+}
+
+static void print_onmatch_spec(struct seq_file *m,
+                              struct hist_trigger_data *hist_data,
+                              struct action_data *data)
+{
+       unsigned int i;
+
+       seq_printf(m, ":onmatch(%s.%s).", data->onmatch.match_event_system,
+                  data->onmatch.match_event);
+
+       seq_printf(m, "%s(", data->onmatch.synth_event->name);
+
+       for (i = 0; i < data->n_params; i++) {
+               if (i)
+                       seq_puts(m, ",");
+               seq_printf(m, "%s", data->params[i]);
+       }
+
+       seq_puts(m, ")");
+}
+
+static bool actions_match(struct hist_trigger_data *hist_data,
+                         struct hist_trigger_data *hist_data_test)
+{
+       unsigned int i, j;
+
+       if (hist_data->n_actions != hist_data_test->n_actions)
+               return false;
+
+       for (i = 0; i < hist_data->n_actions; i++) {
+               struct action_data *data = hist_data->actions[i];
+               struct action_data *data_test = hist_data_test->actions[i];
+
+               if (data->fn != data_test->fn)
+                       return false;
+
+               if (data->n_params != data_test->n_params)
+                       return false;
+
+               for (j = 0; j < data->n_params; j++) {
+                       if (strcmp(data->params[j], data_test->params[j]) != 0)
+                               return false;
+               }
+
+               if (data->fn == action_trace) {
+                       if (strcmp(data->onmatch.synth_event_name,
+                                  data_test->onmatch.synth_event_name) != 0)
+                               return false;
+                       if (strcmp(data->onmatch.match_event_system,
+                                  data_test->onmatch.match_event_system) != 0)
+                               return false;
+                       if (strcmp(data->onmatch.match_event,
+                                  data_test->onmatch.match_event) != 0)
+                               return false;
+               } else if (data->fn == onmax_save) {
+                       if (strcmp(data->onmax.var_str,
+                                  data_test->onmax.var_str) != 0)
+                               return false;
+                       if (strcmp(data->onmax.fn_name,
+                                  data_test->onmax.fn_name) != 0)
+                               return false;
+               }
+       }
+
+       return true;
+}
+
+
+static void print_actions_spec(struct seq_file *m,
+                              struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_actions; i++) {
+               struct action_data *data = hist_data->actions[i];
+
+               if (data->fn == action_trace)
+                       print_onmatch_spec(m, hist_data, data);
+               else if (data->fn == onmax_save)
+                       print_onmax_spec(m, hist_data, data);
+       }
+}
+
+static void destroy_field_var_hists(struct hist_trigger_data *hist_data)
+{
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_field_var_hists; i++) {
+               kfree(hist_data->field_var_hists[i]->cmd);
+               kfree(hist_data->field_var_hists[i]);
+       }
 }
 
 static void destroy_hist_data(struct hist_trigger_data *hist_data)
 {
+       if (!hist_data)
+               return;
+
        destroy_hist_trigger_attrs(hist_data->attrs);
        destroy_hist_fields(hist_data);
        tracing_map_destroy(hist_data->map);
+
+       destroy_actions(hist_data);
+       destroy_field_vars(hist_data);
+       destroy_field_var_hists(hist_data);
+       destroy_synth_var_refs(hist_data);
+
        kfree(hist_data);
 }
 
@@ -738,7 +4460,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
        struct tracing_map *map = hist_data->map;
        struct ftrace_event_field *field;
        struct hist_field *hist_field;
-       int i, idx;
+       int i, idx = 0;
 
        for_each_hist_field(i, hist_data) {
                hist_field = hist_data->fields[i];
@@ -749,6 +4471,9 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
 
                        if (hist_field->flags & HIST_FIELD_FL_STACKTRACE)
                                cmp_fn = tracing_map_cmp_none;
+                       else if (!field)
+                               cmp_fn = tracing_map_cmp_num(hist_field->size,
+                                                            hist_field->is_signed);
                        else if (is_string_field(field))
                                cmp_fn = tracing_map_cmp_string;
                        else
@@ -757,36 +4482,29 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
                        idx = tracing_map_add_key_field(map,
                                                        hist_field->offset,
                                                        cmp_fn);
-
-               } else
+               } else if (!(hist_field->flags & HIST_FIELD_FL_VAR))
                        idx = tracing_map_add_sum_field(map);
 
                if (idx < 0)
                        return idx;
-       }
-
-       return 0;
-}
-
-static bool need_tracing_map_ops(struct hist_trigger_data *hist_data)
-{
-       struct hist_field *key_field;
-       unsigned int i;
-
-       for_each_hist_key_field(i, hist_data) {
-               key_field = hist_data->fields[i];
 
-               if (key_field->flags & HIST_FIELD_FL_EXECNAME)
-                       return true;
+               if (hist_field->flags & HIST_FIELD_FL_VAR) {
+                       idx = tracing_map_add_var(map);
+                       if (idx < 0)
+                               return idx;
+                       hist_field->var.idx = idx;
+                       hist_field->var.hist_data = hist_data;
+               }
        }
 
-       return false;
+       return 0;
 }
 
 static struct hist_trigger_data *
 create_hist_data(unsigned int map_bits,
                 struct hist_trigger_attrs *attrs,
-                struct trace_event_file *file)
+                struct trace_event_file *file,
+                bool remove)
 {
        const struct tracing_map_ops *map_ops = NULL;
        struct hist_trigger_data *hist_data;
@@ -797,6 +4515,12 @@ create_hist_data(unsigned int map_bits,
                return ERR_PTR(-ENOMEM);
 
        hist_data->attrs = attrs;
+       hist_data->remove = remove;
+       hist_data->event_file = file;
+
+       ret = parse_actions(hist_data);
+       if (ret)
+               goto free;
 
        ret = create_hist_fields(hist_data, file);
        if (ret)
@@ -806,8 +4530,7 @@ create_hist_data(unsigned int map_bits,
        if (ret)
                goto free;
 
-       if (need_tracing_map_ops(hist_data))
-               map_ops = &hist_trigger_elt_comm_ops;
+       map_ops = &hist_trigger_elt_data_ops;
 
        hist_data->map = tracing_map_create(map_bits, hist_data->key_size,
                                            map_ops, hist_data);
@@ -820,12 +4543,6 @@ create_hist_data(unsigned int map_bits,
        ret = create_tracing_map_fields(hist_data);
        if (ret)
                goto free;
-
-       ret = tracing_map_init(hist_data->map);
-       if (ret)
-               goto free;
-
-       hist_data->event_file = file;
  out:
        return hist_data;
  free:
@@ -839,18 +4556,39 @@ create_hist_data(unsigned int map_bits,
 }
 
 static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
-                                   struct tracing_map_elt *elt,
-                                   void *rec)
+                                   struct tracing_map_elt *elt, void *rec,
+                                   struct ring_buffer_event *rbe,
+                                   u64 *var_ref_vals)
 {
+       struct hist_elt_data *elt_data;
        struct hist_field *hist_field;
-       unsigned int i;
+       unsigned int i, var_idx;
        u64 hist_val;
 
+       elt_data = elt->private_data;
+       elt_data->var_ref_vals = var_ref_vals;
+
        for_each_hist_val_field(i, hist_data) {
                hist_field = hist_data->fields[i];
-               hist_val = hist_field->fn(hist_field, rec);
+               hist_val = hist_field->fn(hist_field, elt, rbe, rec);
+               if (hist_field->flags & HIST_FIELD_FL_VAR) {
+                       var_idx = hist_field->var.idx;
+                       tracing_map_set_var(elt, var_idx, hist_val);
+                       continue;
+               }
                tracing_map_update_sum(elt, i, hist_val);
        }
+
+       for_each_hist_key_field(i, hist_data) {
+               hist_field = hist_data->fields[i];
+               if (hist_field->flags & HIST_FIELD_FL_VAR) {
+                       hist_val = hist_field->fn(hist_field, elt, rbe, rec);
+                       var_idx = hist_field->var.idx;
+                       tracing_map_set_var(elt, var_idx, hist_val);
+               }
+       }
+
+       update_field_vars(hist_data, elt, rbe, rec);
 }
 
 static inline void add_to_key(char *compound_key, void *key,
@@ -877,15 +4615,31 @@ static inline void add_to_key(char *compound_key, void *key,
        memcpy(compound_key + key_field->offset, key, size);
 }
 
-static void event_hist_trigger(struct event_trigger_data *data, void *rec)
+static void
+hist_trigger_actions(struct hist_trigger_data *hist_data,
+                    struct tracing_map_elt *elt, void *rec,
+                    struct ring_buffer_event *rbe, u64 *var_ref_vals)
+{
+       struct action_data *data;
+       unsigned int i;
+
+       for (i = 0; i < hist_data->n_actions; i++) {
+               data = hist_data->actions[i];
+               data->fn(hist_data, elt, rec, rbe, data, var_ref_vals);
+       }
+}
+
+static void event_hist_trigger(struct event_trigger_data *data, void *rec,
+                              struct ring_buffer_event *rbe)
 {
        struct hist_trigger_data *hist_data = data->private_data;
        bool use_compound_key = (hist_data->n_keys > 1);
        unsigned long entries[HIST_STACKTRACE_DEPTH];
+       u64 var_ref_vals[TRACING_MAP_VARS_MAX];
        char compound_key[HIST_KEY_SIZE_MAX];
+       struct tracing_map_elt *elt = NULL;
        struct stack_trace stacktrace;
        struct hist_field *key_field;
-       struct tracing_map_elt *elt;
        u64 field_contents;
        void *key = NULL;
        unsigned int i;
@@ -906,7 +4660,7 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec)
 
                        key = entries;
                } else {
-                       field_contents = key_field->fn(key_field, rec);
+                       field_contents = key_field->fn(key_field, elt, rbe, rec);
                        if (key_field->flags & HIST_FIELD_FL_STRING) {
                                key = (void *)(unsigned long)field_contents;
                                use_compound_key = true;
@@ -921,9 +4675,18 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec)
        if (use_compound_key)
                key = compound_key;
 
+       if (hist_data->n_var_refs &&
+           !resolve_var_refs(hist_data, key, var_ref_vals, false))
+               return;
+
        elt = tracing_map_insert(hist_data->map, key);
-       if (elt)
-               hist_trigger_elt_update(hist_data, elt, rec);
+       if (!elt)
+               return;
+
+       hist_trigger_elt_update(hist_data, elt, rec, rbe, var_ref_vals);
+
+       if (resolve_var_refs(hist_data, key, var_ref_vals, true))
+               hist_trigger_actions(hist_data, elt, rec, rbe, var_ref_vals);
 }
 
 static void hist_trigger_stacktrace_print(struct seq_file *m,
@@ -952,6 +4715,7 @@ hist_trigger_entry_print(struct seq_file *m,
        struct hist_field *key_field;
        char str[KSYM_SYMBOL_LEN];
        bool multiline = false;
+       const char *field_name;
        unsigned int i;
        u64 uval;
 
@@ -963,26 +4727,33 @@ hist_trigger_entry_print(struct seq_file *m,
                if (i > hist_data->n_vals)
                        seq_puts(m, ", ");
 
+               field_name = hist_field_name(key_field, 0);
+
                if (key_field->flags & HIST_FIELD_FL_HEX) {
                        uval = *(u64 *)(key + key_field->offset);
-                       seq_printf(m, "%s: %llx",
-                                  key_field->field->name, uval);
+                       seq_printf(m, "%s: %llx", field_name, uval);
                } else if (key_field->flags & HIST_FIELD_FL_SYM) {
                        uval = *(u64 *)(key + key_field->offset);
                        sprint_symbol_no_offset(str, uval);
-                       seq_printf(m, "%s: [%llx] %-45s",
-                                  key_field->field->name, uval, str);
+                       seq_printf(m, "%s: [%llx] %-45s", field_name,
+                                  uval, str);
                } else if (key_field->flags & HIST_FIELD_FL_SYM_OFFSET) {
                        uval = *(u64 *)(key + key_field->offset);
                        sprint_symbol(str, uval);
-                       seq_printf(m, "%s: [%llx] %-55s",
-                                  key_field->field->name, uval, str);
+                       seq_printf(m, "%s: [%llx] %-55s", field_name,
+                                  uval, str);
                } else if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
-                       char *comm = elt->private_data;
+                       struct hist_elt_data *elt_data = elt->private_data;
+                       char *comm;
+
+                       if (WARN_ON_ONCE(!elt_data))
+                               return;
+
+                       comm = elt_data->comm;
 
                        uval = *(u64 *)(key + key_field->offset);
-                       seq_printf(m, "%s: %-16s[%10llu]",
-                                  key_field->field->name, comm, uval);
+                       seq_printf(m, "%s: %-16s[%10llu]", field_name,
+                                  comm, uval);
                } else if (key_field->flags & HIST_FIELD_FL_SYSCALL) {
                        const char *syscall_name;
 
@@ -991,8 +4762,8 @@ hist_trigger_entry_print(struct seq_file *m,
                        if (!syscall_name)
                                syscall_name = "unknown_syscall";
 
-                       seq_printf(m, "%s: %-30s[%3llu]",
-                                  key_field->field->name, syscall_name, uval);
+                       seq_printf(m, "%s: %-30s[%3llu]", field_name,
+                                  syscall_name, uval);
                } else if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
                        seq_puts(m, "stacktrace:\n");
                        hist_trigger_stacktrace_print(m,
@@ -1000,15 +4771,14 @@ hist_trigger_entry_print(struct seq_file *m,
                                                      HIST_STACKTRACE_DEPTH);
                        multiline = true;
                } else if (key_field->flags & HIST_FIELD_FL_LOG2) {
-                       seq_printf(m, "%s: ~ 2^%-2llu", key_field->field->name,
+                       seq_printf(m, "%s: ~ 2^%-2llu", field_name,
                                   *(u64 *)(key + key_field->offset));
                } else if (key_field->flags & HIST_FIELD_FL_STRING) {
-                       seq_printf(m, "%s: %-50s", key_field->field->name,
+                       seq_printf(m, "%s: %-50s", field_name,
                                   (char *)(key + key_field->offset));
                } else {
                        uval = *(u64 *)(key + key_field->offset);
-                       seq_printf(m, "%s: %10llu", key_field->field->name,
-                                  uval);
+                       seq_printf(m, "%s: %10llu", field_name, uval);
                }
        }
 
@@ -1021,17 +4791,23 @@ hist_trigger_entry_print(struct seq_file *m,
                   tracing_map_read_sum(elt, HITCOUNT_IDX));
 
        for (i = 1; i < hist_data->n_vals; i++) {
+               field_name = hist_field_name(hist_data->fields[i], 0);
+
+               if (hist_data->fields[i]->flags & HIST_FIELD_FL_VAR ||
+                   hist_data->fields[i]->flags & HIST_FIELD_FL_EXPR)
+                       continue;
+
                if (hist_data->fields[i]->flags & HIST_FIELD_FL_HEX) {
-                       seq_printf(m, "  %s: %10llx",
-                                  hist_data->fields[i]->field->name,
+                       seq_printf(m, "  %s: %10llx", field_name,
                                   tracing_map_read_sum(elt, i));
                } else {
-                       seq_printf(m, "  %s: %10llu",
-                                  hist_data->fields[i]->field->name,
+                       seq_printf(m, "  %s: %10llu", field_name,
                                   tracing_map_read_sum(elt, i));
                }
        }
 
+       print_actions(m, hist_data, elt);
+
        seq_puts(m, "\n");
 }
 
@@ -1102,6 +4878,11 @@ static int hist_show(struct seq_file *m, void *v)
                        hist_trigger_show(m, data, n++);
        }
 
+       if (have_hist_err()) {
+               seq_printf(m, "\nERROR: %s\n", hist_err_str);
+               seq_printf(m, "  Last command: %s\n", last_hist_cmd);
+       }
+
  out_unlock:
        mutex_unlock(&event_mutex);
 
@@ -1120,34 +4901,31 @@ const struct file_operations event_hist_fops = {
        .release = single_release,
 };
 
-static const char *get_hist_field_flags(struct hist_field *hist_field)
+static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 {
-       const char *flags_str = NULL;
+       const char *field_name = hist_field_name(hist_field, 0);
 
-       if (hist_field->flags & HIST_FIELD_FL_HEX)
-               flags_str = "hex";
-       else if (hist_field->flags & HIST_FIELD_FL_SYM)
-               flags_str = "sym";
-       else if (hist_field->flags & HIST_FIELD_FL_SYM_OFFSET)
-               flags_str = "sym-offset";
-       else if (hist_field->flags & HIST_FIELD_FL_EXECNAME)
-               flags_str = "execname";
-       else if (hist_field->flags & HIST_FIELD_FL_SYSCALL)
-               flags_str = "syscall";
-       else if (hist_field->flags & HIST_FIELD_FL_LOG2)
-               flags_str = "log2";
+       if (hist_field->var.name)
+               seq_printf(m, "%s=", hist_field->var.name);
 
-       return flags_str;
-}
+       if (hist_field->flags & HIST_FIELD_FL_CPU)
+               seq_puts(m, "cpu");
+       else if (field_name) {
+               if (hist_field->flags & HIST_FIELD_FL_VAR_REF ||
+                   hist_field->flags & HIST_FIELD_FL_ALIAS)
+                       seq_putc(m, '$');
+               seq_printf(m, "%s", field_name);
+       } else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
+               seq_puts(m, "common_timestamp");
 
-static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
-{
-       seq_printf(m, "%s", hist_field->field->name);
        if (hist_field->flags) {
-               const char *flags_str = get_hist_field_flags(hist_field);
+               if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) &&
+                   !(hist_field->flags & HIST_FIELD_FL_EXPR)) {
+                       const char *flags = get_hist_field_flags(hist_field);
 
-               if (flags_str)
-                       seq_printf(m, ".%s", flags_str);
+                       if (flags)
+                               seq_printf(m, ".%s", flags);
+               }
        }
 }
 
@@ -1156,7 +4934,8 @@ static int event_hist_trigger_print(struct seq_file *m,
                                    struct event_trigger_data *data)
 {
        struct hist_trigger_data *hist_data = data->private_data;
-       struct hist_field *key_field;
+       struct hist_field *field;
+       bool have_var = false;
        unsigned int i;
 
        seq_puts(m, "hist:");
@@ -1167,25 +4946,47 @@ static int event_hist_trigger_print(struct seq_file *m,
        seq_puts(m, "keys=");
 
        for_each_hist_key_field(i, hist_data) {
-               key_field = hist_data->fields[i];
+               field = hist_data->fields[i];
 
                if (i > hist_data->n_vals)
                        seq_puts(m, ",");
 
-               if (key_field->flags & HIST_FIELD_FL_STACKTRACE)
+               if (field->flags & HIST_FIELD_FL_STACKTRACE)
                        seq_puts(m, "stacktrace");
                else
-                       hist_field_print(m, key_field);
+                       hist_field_print(m, field);
        }
 
        seq_puts(m, ":vals=");
 
        for_each_hist_val_field(i, hist_data) {
+               field = hist_data->fields[i];
+               if (field->flags & HIST_FIELD_FL_VAR) {
+                       have_var = true;
+                       continue;
+               }
+
                if (i == HITCOUNT_IDX)
                        seq_puts(m, "hitcount");
                else {
                        seq_puts(m, ",");
-                       hist_field_print(m, hist_data->fields[i]);
+                       hist_field_print(m, field);
+               }
+       }
+
+       if (have_var) {
+               unsigned int n = 0;
+
+               seq_puts(m, ":");
+
+               for_each_hist_val_field(i, hist_data) {
+                       field = hist_data->fields[i];
+
+                       if (field->flags & HIST_FIELD_FL_VAR) {
+                               if (n++)
+                                       seq_puts(m, ",");
+                               hist_field_print(m, field);
+                       }
                }
        }
 
@@ -1193,28 +4994,36 @@ static int event_hist_trigger_print(struct seq_file *m,
 
        for (i = 0; i < hist_data->n_sort_keys; i++) {
                struct tracing_map_sort_key *sort_key;
+               unsigned int idx, first_key_idx;
+
+               /* skip VAR vals */
+               first_key_idx = hist_data->n_vals - hist_data->n_vars;
 
                sort_key = &hist_data->sort_keys[i];
+               idx = sort_key->field_idx;
+
+               if (WARN_ON(idx >= HIST_FIELDS_MAX))
+                       return -EINVAL;
 
                if (i > 0)
                        seq_puts(m, ",");
 
-               if (sort_key->field_idx == HITCOUNT_IDX)
+               if (idx == HITCOUNT_IDX)
                        seq_puts(m, "hitcount");
                else {
-                       unsigned int idx = sort_key->field_idx;
-
-                       if (WARN_ON(idx >= TRACING_MAP_FIELDS_MAX))
-                               return -EINVAL;
-
+                       if (idx >= first_key_idx)
+                               idx += hist_data->n_vars;
                        hist_field_print(m, hist_data->fields[idx]);
                }
 
                if (sort_key->descending)
                        seq_puts(m, ".descending");
        }
-
        seq_printf(m, ":size=%u", (1 << hist_data->map->map_bits));
+       if (hist_data->enable_timestamps)
+               seq_printf(m, ":clock=%s", hist_data->attrs->clock);
+
+       print_actions_spec(m, hist_data);
 
        if (data->filter_str)
                seq_printf(m, " if %s", data->filter_str);
@@ -1242,6 +5051,21 @@ static int event_hist_trigger_init(struct event_trigger_ops *ops,
        return 0;
 }
 
+static void unregister_field_var_hists(struct hist_trigger_data *hist_data)
+{
+       struct trace_event_file *file;
+       unsigned int i;
+       char *cmd;
+       int ret;
+
+       for (i = 0; i < hist_data->n_field_var_hists; i++) {
+               file = hist_data->field_var_hists[i]->hist_data->event_file;
+               cmd = hist_data->field_var_hists[i]->cmd;
+               ret = event_hist_trigger_func(&trigger_hist_cmd, file,
+                                             "!hist", "hist", cmd);
+       }
+}
+
 static void event_hist_trigger_free(struct event_trigger_ops *ops,
                                    struct event_trigger_data *data)
 {
@@ -1254,7 +5078,13 @@ static void event_hist_trigger_free(struct event_trigger_ops *ops,
        if (!data->ref) {
                if (data->name)
                        del_named_trigger(data);
+
                trigger_data_free(data);
+
+               remove_hist_vars(hist_data);
+
+               unregister_field_var_hists(hist_data);
+
                destroy_hist_data(hist_data);
        }
 }
@@ -1381,6 +5211,15 @@ static bool hist_trigger_match(struct event_trigger_data *data,
                        return false;
                if (key_field->offset != key_field_test->offset)
                        return false;
+               if (key_field->size != key_field_test->size)
+                       return false;
+               if (key_field->is_signed != key_field_test->is_signed)
+                       return false;
+               if (!!key_field->var.name != !!key_field_test->var.name)
+                       return false;
+               if (key_field->var.name &&
+                   strcmp(key_field->var.name, key_field_test->var.name) != 0)
+                       return false;
        }
 
        for (i = 0; i < hist_data->n_sort_keys; i++) {
@@ -1396,6 +5235,9 @@ static bool hist_trigger_match(struct event_trigger_data *data,
            (strcmp(data->filter_str, data_test->filter_str) != 0))
                return false;
 
+       if (!actions_match(hist_data, hist_data_test))
+               return false;
+
        return true;
 }
 
@@ -1412,6 +5254,7 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
                if (named_data) {
                        if (!hist_trigger_match(data, named_data, named_data,
                                                true)) {
+                               hist_err("Named hist trigger doesn't match existing named trigger (includes variables): ", hist_data->attrs->name);
                                ret = -EINVAL;
                                goto out;
                        }
@@ -1431,13 +5274,16 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
                                test->paused = false;
                        else if (hist_data->attrs->clear)
                                hist_clear(test);
-                       else
+                       else {
+                               hist_err("Hist trigger already exists", NULL);
                                ret = -EEXIST;
+                       }
                        goto out;
                }
        }
  new:
        if (hist_data->attrs->cont || hist_data->attrs->clear) {
+               hist_err("Can't clear or continue a nonexistent hist trigger", NULL);
                ret = -ENOENT;
                goto out;
        }
@@ -1446,7 +5292,6 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
                data->paused = true;
 
        if (named_data) {
-               destroy_hist_data(data->private_data);
                data->private_data = named_data->private_data;
                set_named_trigger_data(data, named_data);
                data->ops = &event_hist_trigger_named_ops;
@@ -1458,8 +5303,32 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
                        goto out;
        }
 
-       list_add_rcu(&data->list, &file->triggers);
+       if (hist_data->enable_timestamps) {
+               char *clock = hist_data->attrs->clock;
+
+               ret = tracing_set_clock(file->tr, hist_data->attrs->clock);
+               if (ret) {
+                       hist_err("Couldn't set trace_clock: ", clock);
+                       goto out;
+               }
+
+               tracing_set_time_stamp_abs(file->tr, true);
+       }
+
+       if (named_data)
+               destroy_hist_data(hist_data);
+
        ret++;
+ out:
+       return ret;
+}
+
+static int hist_trigger_enable(struct event_trigger_data *data,
+                              struct trace_event_file *file)
+{
+       int ret = 0;
+
+       list_add_tail_rcu(&data->list, &file->triggers);
 
        update_cond_flag(file);
 
@@ -1468,10 +5337,55 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
                update_cond_flag(file);
                ret--;
        }
- out:
+
        return ret;
 }
 
+static bool have_hist_trigger_match(struct event_trigger_data *data,
+                                   struct trace_event_file *file)
+{
+       struct hist_trigger_data *hist_data = data->private_data;
+       struct event_trigger_data *test, *named_data = NULL;
+       bool match = false;
+
+       if (hist_data->attrs->name)
+               named_data = find_named_trigger(hist_data->attrs->name);
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       if (hist_trigger_match(data, test, named_data, false)) {
+                               match = true;
+                               break;
+                       }
+               }
+       }
+
+       return match;
+}
+
+static bool hist_trigger_check_refs(struct event_trigger_data *data,
+                                   struct trace_event_file *file)
+{
+       struct hist_trigger_data *hist_data = data->private_data;
+       struct event_trigger_data *test, *named_data = NULL;
+
+       if (hist_data->attrs->name)
+               named_data = find_named_trigger(hist_data->attrs->name);
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       if (!hist_trigger_match(data, test, named_data, false))
+                               continue;
+                       hist_data = test->private_data;
+                       if (check_var_refs(hist_data))
+                               return true;
+                       break;
+               }
+       }
+
+       return false;
+}
+
 static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
                                    struct event_trigger_data *data,
                                    struct trace_event_file *file)
@@ -1497,17 +5411,55 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
 
        if (unregistered && test->ops->free)
                test->ops->free(test->ops, test);
+
+       if (hist_data->enable_timestamps) {
+               if (!hist_data->remove || unregistered)
+                       tracing_set_time_stamp_abs(file->tr, false);
+       }
+}
+
+static bool hist_file_check_refs(struct trace_event_file *file)
+{
+       struct hist_trigger_data *hist_data;
+       struct event_trigger_data *test;
+
+       list_for_each_entry_rcu(test, &file->triggers, list) {
+               if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       hist_data = test->private_data;
+                       if (check_var_refs(hist_data))
+                               return true;
+               }
+       }
+
+       return false;
 }
 
 static void hist_unreg_all(struct trace_event_file *file)
 {
        struct event_trigger_data *test, *n;
+       struct hist_trigger_data *hist_data;
+       struct synth_event *se;
+       const char *se_name;
+
+       if (hist_file_check_refs(file))
+               return;
 
        list_for_each_entry_safe(test, n, &file->triggers, list) {
                if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+                       hist_data = test->private_data;
                        list_del_rcu(&test->list);
                        trace_event_trigger_enable_disable(file, 0);
+
+                       mutex_lock(&synth_event_mutex);
+                       se_name = trace_event_name(file->event_call);
+                       se = find_synth_event(se_name);
+                       if (se)
+                               se->ref--;
+                       mutex_unlock(&synth_event_mutex);
+
                        update_cond_flag(file);
+                       if (hist_data->enable_timestamps)
+                               tracing_set_time_stamp_abs(file->tr, false);
                        if (test->ops->free)
                                test->ops->free(test->ops, test);
                }
@@ -1523,16 +5475,54 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
        struct hist_trigger_attrs *attrs;
        struct event_trigger_ops *trigger_ops;
        struct hist_trigger_data *hist_data;
-       char *trigger;
+       struct synth_event *se;
+       const char *se_name;
+       bool remove = false;
+       char *trigger, *p;
        int ret = 0;
 
+       if (glob && strlen(glob)) {
+               last_cmd_set(param);
+               hist_err_clear();
+       }
+
        if (!param)
                return -EINVAL;
 
-       /* separate the trigger from the filter (k:v [if filter]) */
-       trigger = strsep(&param, " \t");
-       if (!trigger)
-               return -EINVAL;
+       if (glob[0] == '!')
+               remove = true;
+
+       /*
+        * separate the trigger from the filter (k:v [if filter])
+        * allowing for whitespace in the trigger
+        */
+       p = trigger = param;
+       do {
+               p = strstr(p, "if");
+               if (!p)
+                       break;
+               if (p == param)
+                       return -EINVAL;
+               if (*(p - 1) != ' ' && *(p - 1) != '\t') {
+                       p++;
+                       continue;
+               }
+               if (p >= param + strlen(param) - strlen("if") - 1)
+                       return -EINVAL;
+               if (*(p + strlen("if")) != ' ' && *(p + strlen("if")) != '\t') {
+                       p++;
+                       continue;
+               }
+               break;
+       } while (p);
+
+       if (!p)
+               param = NULL;
+       else {
+               *(p - 1) = '\0';
+               param = strstrip(p);
+               trigger = strstrip(trigger);
+       }
 
        attrs = parse_hist_trigger_attrs(trigger);
        if (IS_ERR(attrs))
@@ -1541,7 +5531,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
        if (attrs->map_bits)
                hist_trigger_bits = attrs->map_bits;
 
-       hist_data = create_hist_data(hist_trigger_bits, attrs, file);
+       hist_data = create_hist_data(hist_trigger_bits, attrs, file, remove);
        if (IS_ERR(hist_data)) {
                destroy_hist_trigger_attrs(attrs);
                return PTR_ERR(hist_data);
@@ -1549,10 +5539,11 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
 
        trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
 
-       ret = -ENOMEM;
        trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
-       if (!trigger_data)
+       if (!trigger_data) {
+               ret = -ENOMEM;
                goto out_free;
+       }
 
        trigger_data->count = -1;
        trigger_data->ops = trigger_ops;
@@ -1570,8 +5561,24 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
                        goto out_free;
        }
 
-       if (glob[0] == '!') {
+       if (remove) {
+               if (!have_hist_trigger_match(trigger_data, file))
+                       goto out_free;
+
+               if (hist_trigger_check_refs(trigger_data, file)) {
+                       ret = -EBUSY;
+                       goto out_free;
+               }
+
                cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+
+               mutex_lock(&synth_event_mutex);
+               se_name = trace_event_name(file->event_call);
+               se = find_synth_event(se_name);
+               if (se)
+                       se->ref--;
+               mutex_unlock(&synth_event_mutex);
+
                ret = 0;
                goto out_free;
        }
@@ -1588,14 +5595,47 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
                goto out_free;
        } else if (ret < 0)
                goto out_free;
+
+       if (get_named_trigger_data(trigger_data))
+               goto enable;
+
+       if (has_hist_vars(hist_data))
+               save_hist_vars(hist_data);
+
+       ret = create_actions(hist_data, file);
+       if (ret)
+               goto out_unreg;
+
+       ret = tracing_map_init(hist_data->map);
+       if (ret)
+               goto out_unreg;
+enable:
+       ret = hist_trigger_enable(trigger_data, file);
+       if (ret)
+               goto out_unreg;
+
+       mutex_lock(&synth_event_mutex);
+       se_name = trace_event_name(file->event_call);
+       se = find_synth_event(se_name);
+       if (se)
+               se->ref++;
+       mutex_unlock(&synth_event_mutex);
+
        /* Just return zero, not the number of registered triggers */
        ret = 0;
  out:
+       if (ret == 0)
+               hist_err_clear();
+
        return ret;
+ out_unreg:
+       cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
  out_free:
        if (cmd_ops->set_filter)
                cmd_ops->set_filter(NULL, trigger_data, NULL);
 
+       remove_hist_vars(hist_data);
+
        kfree(trigger_data);
 
        destroy_hist_data(hist_data);
@@ -1625,7 +5665,8 @@ __init int register_trigger_hist_cmd(void)
 }
 
 static void
-hist_enable_trigger(struct event_trigger_data *data, void *rec)
+hist_enable_trigger(struct event_trigger_data *data, void *rec,
+                   struct ring_buffer_event *event)
 {
        struct enable_trigger_data *enable_data = data->private_data;
        struct event_trigger_data *test;
@@ -1641,7 +5682,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec)
 }
 
 static void
-hist_enable_count_trigger(struct event_trigger_data *data, void *rec)
+hist_enable_count_trigger(struct event_trigger_data *data, void *rec,
+                         struct ring_buffer_event *event)
 {
        if (!data->count)
                return;
@@ -1649,7 +5691,7 @@ hist_enable_count_trigger(struct event_trigger_data *data, void *rec)
        if (data->count != -1)
                (data->count)--;
 
-       hist_enable_trigger(data, rec);
+       hist_enable_trigger(data, rec, event);
 }
 
 static struct event_trigger_ops hist_enable_trigger_ops = {
@@ -1754,3 +5796,31 @@ __init int register_trigger_hist_enable_disable_cmds(void)
 
        return ret;
 }
+
+static __init int trace_events_hist_init(void)
+{
+       struct dentry *entry = NULL;
+       struct dentry *d_tracer;
+       int err = 0;
+
+       d_tracer = tracing_init_dentry();
+       if (IS_ERR(d_tracer)) {
+               err = PTR_ERR(d_tracer);
+               goto err;
+       }
+
+       entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
+                                   NULL, &synth_events_fops);
+       if (!entry) {
+               err = -ENODEV;
+               goto err;
+       }
+
+       return err;
+ err:
+       pr_warn("Could not create tracefs 'synthetic_events' entry\n");
+
+       return err;
+}
+
+fs_initcall(trace_events_hist_init);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 43254c5e7e16..24d42350d738 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -63,7 +63,8 @@ void trigger_data_free(struct event_trigger_data *data)
  * any trigger that should be deferred, ETT_NONE if nothing to defer.
  */
 enum event_trigger_type
-event_triggers_call(struct trace_event_file *file, void *rec)
+event_triggers_call(struct trace_event_file *file, void *rec,
+                   struct ring_buffer_event *event)
 {
        struct event_trigger_data *data;
        enum event_trigger_type tt = ETT_NONE;
@@ -76,7 +77,7 @@ event_triggers_call(struct trace_event_file *file, void *rec)
                if (data->paused)
                        continue;
                if (!rec) {
-                       data->ops->func(data, rec);
+                       data->ops->func(data, rec, event);
                        continue;
                }
                filter = rcu_dereference_sched(data->filter);
@@ -86,7 +87,7 @@ event_triggers_call(struct trace_event_file *file, void *rec)
                        tt |= data->cmd_ops->trigger_type;
                        continue;
                }
-               data->ops->func(data, rec);
+               data->ops->func(data, rec, event);
        }
        return tt;
 }
@@ -108,7 +109,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call);
 void
 event_triggers_post_call(struct trace_event_file *file,
                         enum event_trigger_type tt,
-                        void *rec)
+                        void *rec, struct ring_buffer_event *event)
 {
        struct event_trigger_data *data;
 
@@ -116,7 +117,7 @@ event_triggers_post_call(struct trace_event_file *file,
                if (data->paused)
                        continue;
                if (data->cmd_ops->trigger_type & tt)
-                       data->ops->func(data, rec);
+                       data->ops->func(data, rec, event);
        }
 }
 EXPORT_SYMBOL_GPL(event_triggers_post_call);
@@ -914,8 +915,15 @@ void set_named_trigger_data(struct event_trigger_data *data,
        data->named_data = named_data;
 }
 
+struct event_trigger_data *
+get_named_trigger_data(struct event_trigger_data *data)
+{
+       return data->named_data;
+}
+
 static void
-traceon_trigger(struct event_trigger_data *data, void *rec)
+traceon_trigger(struct event_trigger_data *data, void *rec,
+               struct ring_buffer_event *event)
 {
        if (tracing_is_on())
                return;
@@ -924,7 +932,8 @@ traceon_trigger(struct event_trigger_data *data, void *rec)
 }
 
 static void
-traceon_count_trigger(struct event_trigger_data *data, void *rec)
+traceon_count_trigger(struct event_trigger_data *data, void *rec,
+                     struct ring_buffer_event *event)
 {
        if (tracing_is_on())
                return;
@@ -939,7 +948,8 @@ traceon_count_trigger(struct event_trigger_data *data, void *rec)
 }
 
 static void
-traceoff_trigger(struct event_trigger_data *data, void *rec)
+traceoff_trigger(struct event_trigger_data *data, void *rec,
+                struct ring_buffer_event *event)
 {
        if (!tracing_is_on())
                return;
@@ -948,7 +958,8 @@ traceoff_trigger(struct event_trigger_data *data, void *rec)
 }
 
 static void
-traceoff_count_trigger(struct event_trigger_data *data, void *rec)
+traceoff_count_trigger(struct event_trigger_data *data, void *rec,
+                      struct ring_buffer_event *event)
 {
        if (!tracing_is_on())
                return;
@@ -1045,7 +1056,8 @@ static struct event_command trigger_traceoff_cmd = {
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 static void
-snapshot_trigger(struct event_trigger_data *data, void *rec)
+snapshot_trigger(struct event_trigger_data *data, void *rec,
+                struct ring_buffer_event *event)
 {
        struct trace_event_file *file = data->private_data;
 
@@ -1056,7 +1068,8 @@ snapshot_trigger(struct event_trigger_data *data, void *rec)
 }
 
 static void
-snapshot_count_trigger(struct event_trigger_data *data, void *rec)
+snapshot_count_trigger(struct event_trigger_data *data, void *rec,
+                      struct ring_buffer_event *event)
 {
        if (!data->count)
                return;
@@ -1064,7 +1077,7 @@ snapshot_count_trigger(struct event_trigger_data *data, void *rec)
        if (data->count != -1)
                (data->count)--;
 
-       snapshot_trigger(data, rec);
+       snapshot_trigger(data, rec, event);
 }
 
 static int
@@ -1143,13 +1156,15 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; }
 #define STACK_SKIP 3
 
 static void
-stacktrace_trigger(struct event_trigger_data *data, void *rec)
+stacktrace_trigger(struct event_trigger_data *data, void *rec,
+                  struct ring_buffer_event *event)
 {
        trace_dump_stack(STACK_SKIP);
 }
 
 static void
-stacktrace_count_trigger(struct event_trigger_data *data, void *rec)
+stacktrace_count_trigger(struct event_trigger_data *data, void *rec,
+                        struct ring_buffer_event *event)
 {
        if (!data->count)
                return;
@@ -1157,7 +1172,7 @@ stacktrace_count_trigger(struct event_trigger_data *data, void *rec)
        if (data->count != -1)
                (data->count)--;
 
-       stacktrace_trigger(data, rec);
+       stacktrace_trigger(data, rec, event);
 }
 
 static int
@@ -1219,7 +1234,8 @@ static __init void unregister_trigger_traceon_traceoff_cmds(void)
 }
 
 static void
-event_enable_trigger(struct event_trigger_data *data, void *rec)
+event_enable_trigger(struct event_trigger_data *data, void *rec,
+                    struct ring_buffer_event *event)
 {
        struct enable_trigger_data *enable_data = data->private_data;
 
@@ -1230,7 +1246,8 @@ event_enable_trigger(struct event_trigger_data *data, void *rec)
 }
 
 static void
-event_enable_count_trigger(struct event_trigger_data *data, void *rec)
+event_enable_count_trigger(struct event_trigger_data *data, void *rec,
+                          struct ring_buffer_event *event)
 {
        struct enable_trigger_data *enable_data = data->private_data;
 
@@ -1244,7 +1261,7 @@ event_enable_count_trigger(struct event_trigger_data *data, void *rec)
        if (data->count != -1)
                (data->count)--;
 
-       event_enable_trigger(data, rec);
+       event_enable_trigger(data, rec, event);
 }
 
 int event_enable_trigger_print(struct seq_file *m,
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index d7c8e4ec3d9d..518c61a1bceb 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -279,7 +279,7 @@ static void move_to_next_cpu(void)
         * of this thread, than stop migrating for the duration
         * of the current test.
         */
-       if (!cpumask_equal(current_mask, &current->cpus_allowed))
+       if (!cpumask_equal(current_mask, current->cpus_ptr))
                goto disable;
 
        get_online_cpus();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ea20274a105a..3c40d4174052 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -918,8 +918,8 @@ static int probes_open(struct inode *inode, struct file *file)
 static ssize_t probes_write(struct file *file, const char __user *buffer,
                            size_t count, loff_t *ppos)
 {
-       return traceprobe_probes_write(file, buffer, count, ppos,
-                       create_trace_kprobe);
+       return trace_parse_run_command(file, buffer, count, ppos,
+                                      create_trace_kprobe);
 }
 
 static const struct file_operations kprobe_events_ops = {
@@ -1444,9 +1444,9 @@ static __init int kprobe_trace_self_tests_init(void)
 
        pr_info("Testing kprobe tracing: ");
 
-       ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
-                                 "$stack $stack0 +0($stack)",
-                                 create_trace_kprobe);
+       ret = trace_run_command("p:testprobe kprobe_trace_selftest_target "
+                               "$stack $stack0 +0($stack)",
+                               create_trace_kprobe);
        if (WARN_ON_ONCE(ret)) {
                pr_warn("error on probing function entry.\n");
                warn++;
@@ -1466,8 +1466,8 @@ static __init int kprobe_trace_self_tests_init(void)
                }
        }
 
-       ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
-                                 "$retval", create_trace_kprobe);
+       ret = trace_run_command("r:testprobe2 kprobe_trace_selftest_target "
+                               "$retval", create_trace_kprobe);
        if (WARN_ON_ONCE(ret)) {
                pr_warn("error on probing function return.\n");
                warn++;
@@ -1537,13 +1537,13 @@ static __init int kprobe_trace_self_tests_init(void)
                        disable_trace_kprobe(tk, file);
        }
 
-       ret = traceprobe_command("-:testprobe", create_trace_kprobe);
+       ret = trace_run_command("-:testprobe", create_trace_kprobe);
        if (WARN_ON_ONCE(ret)) {
                pr_warn("error on deleting a probe.\n");
                warn++;
        }
 
-       ret = traceprobe_command("-:testprobe2", create_trace_kprobe);
+       ret = trace_run_command("-:testprobe2", create_trace_kprobe);
        if (WARN_ON_ONCE(ret)) {
                pr_warn("error on deleting a probe.\n");
                warn++;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 4500b00e4e36..74a4bfc2c6b7 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -447,6 +447,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
        char hardsoft_irq;
        char need_resched;
+       char need_resched_lazy;
        char irqs_off;
        int hardirq;
        int softirq;
@@ -477,6 +478,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
                break;
        }
 
+       need_resched_lazy =
+               (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.';
+
        hardsoft_irq =
                (nmi && hardirq)     ? 'Z' :
                nmi                  ? 'z' :
@@ -485,14 +489,25 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
                softirq              ? 's' :
                                       '.' ;
 
-       trace_seq_printf(s, "%c%c%c",
-                        irqs_off, need_resched, hardsoft_irq);
+       trace_seq_printf(s, "%c%c%c%c",
+                        irqs_off, need_resched, need_resched_lazy,
+                        hardsoft_irq);
 
        if (entry->preempt_count)
                trace_seq_printf(s, "%x", entry->preempt_count);
        else
                trace_seq_putc(s, '.');
 
+       if (entry->preempt_lazy_count)
+               trace_seq_printf(s, "%x", entry->preempt_lazy_count);
+       else
+               trace_seq_putc(s, '.');
+
+       if (entry->migrate_disable)
+               trace_seq_printf(s, "%x", entry->migrate_disable);
+       else
+               trace_seq_putc(s, '.');
+
        return !trace_seq_has_overflowed(s);
 }
 
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index fe4513330412..daf54bda4dc8 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -621,92 +621,6 @@ void traceprobe_free_probe_arg(struct probe_arg *arg)
        kfree(arg->comm);
 }
 
-int traceprobe_command(const char *buf, int (*createfn)(int, char **))
-{
-       char **argv;
-       int argc, ret;
-
-       argc = 0;
-       ret = 0;
-       argv = argv_split(GFP_KERNEL, buf, &argc);
-       if (!argv)
-               return -ENOMEM;
-
-       if (argc)
-               ret = createfn(argc, argv);
-
-       argv_free(argv);
-
-       return ret;
-}
-
-#define WRITE_BUFSIZE  4096
-
-ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer,
-                               size_t count, loff_t *ppos,
-                               int (*createfn)(int, char **))
-{
-       char *kbuf, *buf, *tmp;
-       int ret = 0;
-       size_t done = 0;
-       size_t size;
-
-       kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
-       if (!kbuf)
-               return -ENOMEM;
-
-       while (done < count) {
-               size = count - done;
-
-               if (size >= WRITE_BUFSIZE)
-                       size = WRITE_BUFSIZE - 1;
-
-               if (copy_from_user(kbuf, buffer + done, size)) {
-                       ret = -EFAULT;
-                       goto out;
-               }
-               kbuf[size] = '\0';
-               buf = kbuf;
-               do {
-                       tmp = strchr(buf, '\n');
-                       if (tmp) {
-                               *tmp = '\0';
-                               size = tmp - buf + 1;
-                       } else {
-                               size = strlen(buf);
-                               if (done + size < count) {
-                                       if (buf != kbuf)
-                                               break;
-                                       /* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */
-                                       pr_warn("Line length is too long: Should be less than %d\n",
-                                               WRITE_BUFSIZE - 2);
-                                       ret = -EINVAL;
-                                       goto out;
-                               }
-                       }
-                       done += size;
-
-                       /* Remove comments */
-                       tmp = strchr(buf, '#');
-
-                       if (tmp)
-                               *tmp = '\0';
-
-                       ret = traceprobe_command(buf, createfn);
-                       if (ret)
-                               goto out;
-                       buf += size;
-
-               } while (done < count);
-       }
-       ret = done;
-
-out:
-       kfree(kbuf);
-
-       return ret;
-}
-
 static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
                           bool is_return)
 {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index dc39472ca9e4..a0d750e3d17c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -42,7 +42,6 @@
 
 #define MAX_TRACE_ARGS         128
 #define MAX_ARGSTR_LEN         63
-#define MAX_EVENT_NAME_LEN     64
 #define MAX_STRING_SIZE                PATH_MAX
 
 /* Reserved field names */
@@ -356,12 +355,6 @@ extern void traceprobe_free_probe_arg(struct probe_arg *arg);
 
 extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
 
-extern ssize_t traceprobe_probes_write(struct file *file,
-               const char __user *buffer, size_t count, loff_t *ppos,
-               int (*createfn)(int, char**));
-
-extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
-
 /* Sum up total data length for dynamic arraies (strings) */
 static nokprobe_inline int
 __get_data_size(struct trace_probe *tp, struct pt_regs *regs)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index ea0d90a31fc9..2ccfbb8efeb2 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -647,7 +647,7 @@ static int probes_open(struct inode *inode, struct file *file)
 static ssize_t probes_write(struct file *file, const char __user *buffer,
                            size_t count, loff_t *ppos)
 {
-       return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe);
+       return trace_parse_run_command(file, buffer, count, ppos, create_trace_uprobe);
 }
 
 static const struct file_operations uprobe_events_ops = {
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 305039b122fa..5cadb1b8b5fe 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -66,6 +66,73 @@ u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i)
        return (u64)atomic64_read(&elt->fields[i].sum);
 }
 
+/**
+ * tracing_map_set_var - Assign a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ * @n: The value to assign
+ *
+ * Assign n to variable i associated with the specified tracing_map_elt
+ * instance.  The index i is the index returned by the call to
+ * tracing_map_add_var() when the tracing map was set up.
+ */
+void tracing_map_set_var(struct tracing_map_elt *elt, unsigned int i, u64 n)
+{
+       atomic64_set(&elt->vars[i], n);
+       elt->var_set[i] = true;
+}
+
+/**
+ * tracing_map_var_set - Return whether or not a variable has been set
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Return true if the variable has been set, false otherwise.  The
+ * index i is the index returned by the call to tracing_map_add_var()
+ * when the tracing map was set up.
+ */
+bool tracing_map_var_set(struct tracing_map_elt *elt, unsigned int i)
+{
+       return elt->var_set[i];
+}
+
+/**
+ * tracing_map_read_var - Return the value of a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Retrieve the value of the variable i associated with the specified
+ * tracing_map_elt instance.  The index i is the index returned by the
+ * call to tracing_map_add_var() when the tracing map was set
+ * up.
+ *
+ * Return: The variable value associated with field i for elt.
+ */
+u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i)
+{
+       return (u64)atomic64_read(&elt->vars[i]);
+}
+
+/**
+ * tracing_map_read_var_once - Return and reset a tracing_map_elt's variable field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given variable associated with the tracing_map_elt
+ *
+ * Retrieve the value of the variable i associated with the specified
+ * tracing_map_elt instance, and reset the variable to the 'not set'
+ * state.  The index i is the index returned by the call to
+ * tracing_map_add_var() when the tracing map was set up.  The reset
+ * essentially makes the variable a read-once variable if it's only
+ * accessed using this function.
+ *
+ * Return: The variable value associated with field i for elt.
+ */
+u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i)
+{
+       elt->var_set[i] = false;
+       return (u64)atomic64_read(&elt->vars[i]);
+}
+
 int tracing_map_cmp_string(void *val_a, void *val_b)
 {
        char *a = val_a;
@@ -170,6 +237,28 @@ int tracing_map_add_sum_field(struct tracing_map *map)
        return tracing_map_add_field(map, tracing_map_cmp_atomic64);
 }
 
+/**
+ * tracing_map_add_var - Add a field describing a tracing_map var
+ * @map: The tracing_map
+ *
+ * Add a var to the map and return the index identifying it in the map
+ * and associated tracing_map_elts.  This is the index used for
+ * instance to update a var for a particular tracing_map_elt using
+ * tracing_map_update_var() or reading it via tracing_map_read_var().
+ *
+ * Return: The index identifying the var in the map and associated
+ * tracing_map_elts, or -EINVAL on error.
+ */
+int tracing_map_add_var(struct tracing_map *map)
+{
+       int ret = -EINVAL;
+
+       if (map->n_vars < TRACING_MAP_VARS_MAX)
+               ret = map->n_vars++;
+
+       return ret;
+}
+
 /**
  * tracing_map_add_key_field - Add a field describing a tracing_map key
  * @map: The tracing_map
@@ -280,6 +369,11 @@ static void tracing_map_elt_clear(struct tracing_map_elt *elt)
                if (elt->fields[i].cmp_fn == tracing_map_cmp_atomic64)
                        atomic64_set(&elt->fields[i].sum, 0);
 
+       for (i = 0; i < elt->map->n_vars; i++) {
+               atomic64_set(&elt->vars[i], 0);
+               elt->var_set[i] = false;
+       }
+
        if (elt->map->ops && elt->map->ops->elt_clear)
                elt->map->ops->elt_clear(elt);
 }
@@ -306,6 +400,8 @@ static void tracing_map_elt_free(struct tracing_map_elt *elt)
        if (elt->map->ops && elt->map->ops->elt_free)
                elt->map->ops->elt_free(elt);
        kfree(elt->fields);
+       kfree(elt->vars);
+       kfree(elt->var_set);
        kfree(elt->key);
        kfree(elt);
 }
@@ -333,6 +429,18 @@ static struct tracing_map_elt *tracing_map_elt_alloc(struct tracing_map *map)
                goto free;
        }
 
+       elt->vars = kcalloc(map->n_vars, sizeof(*elt->vars), GFP_KERNEL);
+       if (!elt->vars) {
+               err = -ENOMEM;
+               goto free;
+       }
+
+       elt->var_set = kcalloc(map->n_vars, sizeof(*elt->var_set), GFP_KERNEL);
+       if (!elt->var_set) {
+               err = -ENOMEM;
+               goto free;
+       }
+
        tracing_map_elt_init_fields(elt);
 
        if (map->ops && map->ops->elt_alloc) {
@@ -414,7 +522,9 @@ static inline struct tracing_map_elt *
 __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 {
        u32 idx, key_hash, test_key;
+       int dup_try = 0;
        struct tracing_map_entry *entry;
+       struct tracing_map_elt *val;
 
        key_hash = jhash(key, map->key_size, 0);
        if (key_hash == 0)
@@ -426,10 +536,33 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
                entry = TRACING_MAP_ENTRY(map->map, idx);
                test_key = entry->key;
 
-               if (test_key && test_key == key_hash && entry->val &&
-                   keys_match(key, entry->val->key, map->key_size)) {
-                       atomic64_inc(&map->hits);
-                       return entry->val;
+               if (test_key && test_key == key_hash) {
+                       val = READ_ONCE(entry->val);
+                       if (val &&
+                           keys_match(key, val->key, map->key_size)) {
+                               if (!lookup_only)
+                                       atomic64_inc(&map->hits);
+                               return val;
+                       } else if (unlikely(!val)) {
+                               /*
+                                * The key is present. But, val (pointer to elt
+                                * struct) is still NULL. which means some other
+                                * thread is in the process of inserting an
+                                * element.
+                                *
+                                * On top of that, it's key_hash is same as the
+                                * one being inserted right now. So, it's
+                                * possible that the element has the same
+                                * key as well.
+                                */
+
+                               dup_try++;
+                               if (dup_try > map->map_size) {
+                                       atomic64_inc(&map->drops);
+                                       break;
+                               }
+                               continue;
+                       }
                }
 
                if (!test_key) {
@@ -451,6 +584,13 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
                                atomic64_inc(&map->hits);
 
                                return entry->val;
+                       } else {
+                               /*
+                                * cmpxchg() failed. Loop around once
+                                * more to check what key was inserted.
+                                */
+                               dup_try++;
+                               continue;
                        }
                }
 
@@ -815,67 +955,15 @@ create_sort_entry(void *key, struct tracing_map_elt *elt)
        return sort_entry;
 }
 
-static struct tracing_map_elt *copy_elt(struct tracing_map_elt *elt)
-{
-       struct tracing_map_elt *dup_elt;
-       unsigned int i;
-
-       dup_elt = tracing_map_elt_alloc(elt->map);
-       if (IS_ERR(dup_elt))
-               return NULL;
-
-       if (elt->map->ops && elt->map->ops->elt_copy)
-               elt->map->ops->elt_copy(dup_elt, elt);
-
-       dup_elt->private_data = elt->private_data;
-       memcpy(dup_elt->key, elt->key, elt->map->key_size);
-
-       for (i = 0; i < elt->map->n_fields; i++) {
-               atomic64_set(&dup_elt->fields[i].sum,
-                            atomic64_read(&elt->fields[i].sum));
-               dup_elt->fields[i].cmp_fn = elt->fields[i].cmp_fn;
-       }
-
-       return dup_elt;
-}
-
-static int merge_dup(struct tracing_map_sort_entry **sort_entries,
-                    unsigned int target, unsigned int dup)
-{
-       struct tracing_map_elt *target_elt, *elt;
-       bool first_dup = (target - dup) == 1;
-       int i;
-
-       if (first_dup) {
-               elt = sort_entries[target]->elt;
-               target_elt = copy_elt(elt);
-               if (!target_elt)
-                       return -ENOMEM;
-               sort_entries[target]->elt = target_elt;
-               sort_entries[target]->elt_copied = true;
-       } else
-               target_elt = sort_entries[target]->elt;
-
-       elt = sort_entries[dup]->elt;
-
-       for (i = 0; i < elt->map->n_fields; i++)
-               atomic64_add(atomic64_read(&elt->fields[i].sum),
-                            &target_elt->fields[i].sum);
-
-       sort_entries[dup]->dup = true;
-
-       return 0;
-}
-
-static int merge_dups(struct tracing_map_sort_entry **sort_entries,
+static void detect_dups(struct tracing_map_sort_entry **sort_entries,
                      int n_entries, unsigned int key_size)
 {
        unsigned int dups = 0, total_dups = 0;
-       int err, i, j;
+       int i;
        void *key;
 
        if (n_entries < 2)
-               return total_dups;
+               return;
 
        sort(sort_entries, n_entries, sizeof(struct tracing_map_sort_entry *),
             (int (*)(const void *, const void *))cmp_entries_dup, NULL);
@@ -884,30 +972,14 @@ static int merge_dups(struct tracing_map_sort_entry **sort_entries,
        for (i = 1; i < n_entries; i++) {
                if (!memcmp(sort_entries[i]->key, key, key_size)) {
                        dups++; total_dups++;
-                       err = merge_dup(sort_entries, i - dups, i);
-                       if (err)
-                               return err;
                        continue;
                }
                key = sort_entries[i]->key;
                dups = 0;
        }
 
-       if (!total_dups)
-               return total_dups;
-
-       for (i = 0, j = 0; i < n_entries; i++) {
-               if (!sort_entries[i]->dup) {
-                       sort_entries[j] = sort_entries[i];
-                       if (j++ != i)
-                               sort_entries[i] = NULL;
-               } else {
-                       destroy_sort_entry(sort_entries[i]);
-                       sort_entries[i] = NULL;
-               }
-       }
-
-       return total_dups;
+       WARN_ONCE(total_dups > 0,
+                 "Duplicates detected: %d\n", total_dups);
 }
 
 static bool is_key(struct tracing_map *map, unsigned int field_idx)
@@ -1033,10 +1105,7 @@ int tracing_map_sort_entries(struct tracing_map *map,
                return 1;
        }
 
-       ret = merge_dups(entries, n_entries, map->key_size);
-       if (ret < 0)
-               goto free;
-       n_entries -= ret;
+       detect_dups(entries, n_entries, map->key_size);
 
        if (is_key(map, sort_keys[0].field_idx))
                cmp_entries_fn = cmp_entries_key;
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
index ab0ca77331d0..053eb92b2d31 100644
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -6,10 +6,11 @@
 #define TRACING_MAP_BITS_MAX           17
 #define TRACING_MAP_BITS_MIN           7
 
-#define TRACING_MAP_KEYS_MAX           2
+#define TRACING_MAP_KEYS_MAX           3
 #define TRACING_MAP_VALS_MAX           3
 #define TRACING_MAP_FIELDS_MAX         (TRACING_MAP_KEYS_MAX + \
                                         TRACING_MAP_VALS_MAX)
+#define TRACING_MAP_VARS_MAX           16
 #define TRACING_MAP_SORT_KEYS_MAX      2
 
 typedef int (*tracing_map_cmp_fn_t) (void *val_a, void *val_b);
@@ -137,6 +138,8 @@ struct tracing_map_field {
 struct tracing_map_elt {
        struct tracing_map              *map;
        struct tracing_map_field        *fields;
+       atomic64_t                      *vars;
+       bool                            *var_set;
        void                            *key;
        void                            *private_data;
 };
@@ -192,6 +195,7 @@ struct tracing_map {
        int                             key_idx[TRACING_MAP_KEYS_MAX];
        unsigned int                    n_keys;
        struct tracing_map_sort_key     sort_key;
+       unsigned int                    n_vars;
        atomic64_t                      hits;
        atomic64_t                      drops;
 };
@@ -215,11 +219,6 @@ struct tracing_map {
  *     Element allocation occurs before tracing begins, when the
  *     tracing_map_init() call is made by client code.
  *
- * @elt_copy: At certain points in the lifetime of an element, it may
- *     need to be copied.  The copy should include a copy of the
- *     client-allocated data, which can be copied into the 'to'
- *     element from the 'from' element.
- *
  * @elt_free: When a tracing_map_elt is freed, this function is called
  *     and allows client-allocated per-element data to be freed.
  *
@@ -233,8 +232,6 @@ struct tracing_map {
  */
 struct tracing_map_ops {
        int                     (*elt_alloc)(struct tracing_map_elt *elt);
-       void                    (*elt_copy)(struct tracing_map_elt *to,
-                                           struct tracing_map_elt *from);
        void                    (*elt_free)(struct tracing_map_elt *elt);
        void                    (*elt_clear)(struct tracing_map_elt *elt);
        void                    (*elt_init)(struct tracing_map_elt *elt);
@@ -248,6 +245,7 @@ tracing_map_create(unsigned int map_bits,
 extern int tracing_map_init(struct tracing_map *map);
 
 extern int tracing_map_add_sum_field(struct tracing_map *map);
+extern int tracing_map_add_var(struct tracing_map *map);
 extern int tracing_map_add_key_field(struct tracing_map *map,
                                     unsigned int offset,
                                     tracing_map_cmp_fn_t cmp_fn);
@@ -267,7 +265,13 @@ extern int tracing_map_cmp_none(void *val_a, void *val_b);
 
 extern void tracing_map_update_sum(struct tracing_map_elt *elt,
                                   unsigned int i, u64 n);
+extern void tracing_map_set_var(struct tracing_map_elt *elt,
+                               unsigned int i, u64 n);
+extern bool tracing_map_var_set(struct tracing_map_elt *elt, unsigned int i);
 extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i);
+
 extern void tracing_map_set_field_descr(struct tracing_map *map,
                                        unsigned int i,
                                        unsigned int key_offset,
diff --git a/kernel/user.c b/kernel/user.c
index 00281add65b2..f4cf1841f2fd 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -162,11 +162,11 @@ void free_uid(struct user_struct *up)
        if (!up)
                return;
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
                free_user(up, flags);
        else
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
 }
 
 struct user_struct *alloc_uid(kuid_t uid)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 087994b23f8b..ea4c09109ce4 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -462,7 +462,7 @@ static void watchdog_enable(unsigned int cpu)
         * Start the timer first to prevent the NMI watchdog triggering
         * before the timer has a chance to fire.
         */
-       hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
        hrtimer->function = watchdog_timer_fn;
        hrtimer_start(hrtimer, ns_to_ktime(sample_period),
                      HRTIMER_MODE_REL_PINNED);
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 4ece6028007a..210dccc57c04 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -24,6 +24,8 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 static DEFINE_PER_CPU(struct perf_event *, dead_event);
+static DEFINE_RAW_SPINLOCK(watchdog_output_lock);
+
 static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
@@ -134,6 +136,13 @@ static void watchdog_overflow_callback(struct perf_event *event,
                /* only print hardlockups once */
                if (__this_cpu_read(hard_watchdog_warn) == true)
                        return;
+               /*
+                * If early-printk is enabled then make sure we do not
+                * lock up in printk() and kill console logging:
+                */
+               printk_kill();
+
+               raw_spin_lock(&watchdog_output_lock);
 
                pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
                print_modules();
@@ -151,6 +160,7 @@ static void watchdog_overflow_callback(struct perf_event *event,
                                !test_and_set_bit(0, &hardlockup_allcpu_dumped))
                        trigger_allbutself_cpu_backtrace();
 
+               raw_spin_unlock(&watchdog_output_lock);
                if (hardlockup_panic)
                        nmi_panic(regs, "Hard LOCKUP");
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 08bc551976b2..76297cce5602 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -49,6 +49,8 @@
 #include <linux/moduleparam.h>
 #include <linux/uaccess.h>
 #include <linux/nmi.h>
+#include <linux/locallock.h>
+#include <linux/delay.h>
 
 #include "workqueue_internal.h"
 
@@ -123,11 +125,16 @@ enum {
  *    cpu or grabbing pool->lock is enough for read access.  If
  *    POOL_DISASSOCIATED is set, it's identical to L.
  *
+ *    On RT we need the extra protection via rt_lock_idle_list() for
+ *    the list manipulations against read access from
+ *    wq_worker_sleeping(). All other places are nicely serialized via
+ *    pool->lock.
+ *
  * A: pool->attach_mutex protected.
  *
  * PL: wq_pool_mutex protected.
  *
- * PR: wq_pool_mutex protected for writes.  Sched-RCU protected for reads.
+ * PR: wq_pool_mutex protected for writes.  RCU protected for reads.
  *
  * PW: wq_pool_mutex and wq->mutex protected for writes.  Either for reads.
  *
@@ -136,7 +143,7 @@ enum {
  *
  * WQ: wq->mutex protected.
  *
- * WR: wq->mutex protected for writes.  Sched-RCU protected for reads.
+ * WR: wq->mutex protected for writes.  RCU protected for reads.
  *
  * MD: wq_mayday_lock protected.
  */
@@ -186,7 +193,7 @@ struct worker_pool {
        atomic_t                nr_running ____cacheline_aligned_in_smp;
 
        /*
-        * Destruction of pool is sched-RCU protected to allow dereferences
+        * Destruction of pool is RCU protected to allow dereferences
         * from get_work_pool().
         */
        struct rcu_head         rcu;
@@ -215,7 +222,7 @@ struct pool_workqueue {
        /*
         * Release of unbound pwq is punted to system_wq.  See put_pwq()
         * and pwq_unbound_release_workfn() for details.  pool_workqueue
-        * itself is also sched-RCU protected so that the first pwq can be
+        * itself is also RCU protected so that the first pwq can be
         * determined without grabbing wq->mutex.
         */
        struct work_struct      unbound_release_work;
@@ -352,6 +359,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient_wq);
 struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
 
+static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock);
+
 static int worker_thread(void *__worker);
 static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
 
@@ -359,20 +368,20 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
 #include <trace/events/workqueue.h>
 
 #define assert_rcu_or_pool_mutex()                                     \
-       RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&                 \
+       RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&                       \
                         !lockdep_is_held(&wq_pool_mutex),              \
-                        "sched RCU or wq_pool_mutex should be held")
+                        "RCU or wq_pool_mutex should be held")
 
 #define assert_rcu_or_wq_mutex(wq)                                     \
-       RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&                 \
+       RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&                       \
                         !lockdep_is_held(&wq->mutex),                  \
-                        "sched RCU or wq->mutex should be held")
+                        "RCU or wq->mutex should be held")
 
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)                       \
-       RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&                 \
+       RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&                       \
                         !lockdep_is_held(&wq->mutex) &&                \
                         !lockdep_is_held(&wq_pool_mutex),              \
-                        "sched RCU, wq->mutex or wq_pool_mutex should be held")
+                        "RCU, wq->mutex or wq_pool_mutex should be held")
 
 #define for_each_cpu_worker_pool(pool, cpu)                            \
        for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];               \
@@ -384,7 +393,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
  * @pool: iteration cursor
  * @pi: integer used for iteration
  *
- * This must be called either with wq_pool_mutex held or sched RCU read
+ * This must be called either with wq_pool_mutex held or RCU read
  * locked.  If the pool needs to be used beyond the locking in effect, the
  * caller is responsible for guaranteeing that the pool stays online.
  *
@@ -416,7 +425,7 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
  * @pwq: iteration cursor
  * @wq: the target workqueue
  *
- * This must be called either with wq->mutex held or sched RCU read locked.
+ * This must be called either with wq->mutex held or RCU read locked.
  * If the pwq needs to be used beyond the locking in effect, the caller is
  * responsible for guaranteeing that the pwq stays online.
  *
@@ -428,6 +437,31 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
                if (({ assert_rcu_or_wq_mutex(wq); false; })) { }       \
                else
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static inline void rt_lock_idle_list(struct worker_pool *pool)
+{
+       preempt_disable();
+}
+static inline void rt_unlock_idle_list(struct worker_pool *pool)
+{
+       preempt_enable();
+}
+static inline void sched_lock_idle_list(struct worker_pool *pool) { }
+static inline void sched_unlock_idle_list(struct worker_pool *pool) { }
+#else
+static inline void rt_lock_idle_list(struct worker_pool *pool) { }
+static inline void rt_unlock_idle_list(struct worker_pool *pool) { }
+static inline void sched_lock_idle_list(struct worker_pool *pool)
+{
+       spin_lock_irq(&pool->lock);
+}
+static inline void sched_unlock_idle_list(struct worker_pool *pool)
+{
+       spin_unlock_irq(&pool->lock);
+}
+#endif
+
+
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 
 static struct debug_obj_descr work_debug_descr;
@@ -552,7 +586,7 @@ static int worker_pool_assign_id(struct worker_pool *pool)
  * @wq: the target workqueue
  * @node: the node ID
  *
- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU
+ * This must be called with any of wq_pool_mutex, wq->mutex or RCU
  * read locked.
  * If the pwq needs to be used beyond the locking in effect, the caller is
  * responsible for guaranteeing that the pwq stays online.
@@ -696,8 +730,8 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work)
  * @work: the work item of interest
  *
  * Pools are created and destroyed under wq_pool_mutex, and allows read
- * access under sched-RCU read lock.  As such, this function should be
- * called under wq_pool_mutex or with preemption disabled.
+ * access under RCU read lock.  As such, this function should be
+ * called under wq_pool_mutex or inside of a rcu_read_lock() region.
  *
  * All fields of the returned pool are accessible as long as the above
  * mentioned locking is in effect.  If the returned pool needs to be used
@@ -834,50 +868,45 @@ static struct worker *first_idle_worker(struct worker_pool *pool)
  */
 static void wake_up_worker(struct worker_pool *pool)
 {
-       struct worker *worker = first_idle_worker(pool);
+       struct worker *worker;
+
+       rt_lock_idle_list(pool);
+
+       worker = first_idle_worker(pool);
 
        if (likely(worker))
                wake_up_process(worker->task);
+
+       rt_unlock_idle_list(pool);
 }
 
 /**
- * wq_worker_waking_up - a worker is waking up
+ * wq_worker_running - a worker is running again
  * @task: task waking up
- * @cpu: CPU @task is waking up to
  *
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu)
+void wq_worker_running(struct task_struct *task)
 {
        struct worker *worker = kthread_data(task);
 
-       if (!(worker->flags & WORKER_NOT_RUNNING)) {
-               WARN_ON_ONCE(worker->pool->cpu != cpu);
+       if (!worker->sleeping)
+               return;
+       if (!(worker->flags & WORKER_NOT_RUNNING))
                atomic_inc(&worker->pool->nr_running);
-       }
+       worker->sleeping = 0;
 }
 
 /**
  * wq_worker_sleeping - a worker is going to sleep
  * @task: task going to sleep
  *
- * This function is called during schedule() when a busy worker is
- * going to sleep.  Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * Return:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task)
+void wq_worker_sleeping(struct task_struct *task)
 {
-       struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+       struct worker *worker = kthread_data(task);
        struct worker_pool *pool;
 
        /*
@@ -886,29 +915,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
         * checking NOT_RUNNING.
         */
        if (worker->flags & WORKER_NOT_RUNNING)
-               return NULL;
+               return;
 
        pool = worker->pool;
 
-       /* this can only happen on the local cpu */
-       if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id()))
-               return NULL;
+       if (WARN_ON_ONCE(worker->sleeping))
+               return;
+
+       worker->sleeping = 1;
 
        /*
         * The counterpart of the following dec_and_test, implied mb,
         * worklist not empty test sequence is in insert_work().
         * Please read comment there.
-        *
-        * NOT_RUNNING is clear.  This means that we're bound to and
-        * running on the local cpu w/ rq lock held and preemption
-        * disabled, which in turn means that none else could be
-        * manipulating idle_list, so dereferencing idle_list without pool
-        * lock is safe.
         */
        if (atomic_dec_and_test(&pool->nr_running) &&
-           !list_empty(&pool->worklist))
-               to_wakeup = first_idle_worker(pool);
-       return to_wakeup ? to_wakeup->task : NULL;
+           !list_empty(&pool->worklist)) {
+               sched_lock_idle_list(pool);
+               wake_up_worker(pool);
+               sched_unlock_idle_list(pool);
+       }
 }
 
 /**
@@ -1102,12 +1128,14 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq)
 {
        if (pwq) {
                /*
-                * As both pwqs and pools are sched-RCU protected, the
+                * As both pwqs and pools are RCU protected, the
                 * following lock operations are safe.
                 */
-               spin_lock_irq(&pwq->pool->lock);
+               rcu_read_lock();
+               local_spin_lock_irq(pendingb_lock, &pwq->pool->lock);
                put_pwq(pwq);
-               spin_unlock_irq(&pwq->pool->lock);
+               local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock);
+               rcu_read_unlock();
        }
 }
 
@@ -1211,7 +1239,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
        struct worker_pool *pool;
        struct pool_workqueue *pwq;
 
-       local_irq_save(*flags);
+       local_lock_irqsave(pendingb_lock, *flags);
 
        /* try to steal the timer if it exists */
        if (is_dwork) {
@@ -1230,6 +1258,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
        if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
                return 0;
 
+       rcu_read_lock();
        /*
         * The queueing is in progress, or it is already queued. Try to
         * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
@@ -1268,14 +1297,16 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
                set_work_pool_and_keep_pending(work, pool->id);
 
                spin_unlock(&pool->lock);
+               rcu_read_unlock();
                return 1;
        }
        spin_unlock(&pool->lock);
 fail:
-       local_irq_restore(*flags);
+       rcu_read_unlock();
+       local_unlock_irqrestore(pendingb_lock, *flags);
        if (work_is_canceling(work))
                return -ENOENT;
-       cpu_relax();
+       cpu_chill();
        return -EAGAIN;
 }
 
@@ -1377,7 +1408,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
         * queued or lose PENDING.  Grabbing PENDING and queueing should
         * happen with IRQ disabled.
         */
-       WARN_ON_ONCE(!irqs_disabled());
+       WARN_ON_ONCE_NONRT(!irqs_disabled());
 
        debug_work_activate(work);
 
@@ -1385,6 +1416,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
        if (unlikely(wq->flags & __WQ_DRAINING) &&
            WARN_ON_ONCE(!is_chained_work(wq)))
                return;
+       rcu_read_lock();
 retry:
        if (req_cpu == WORK_CPU_UNBOUND)
                cpu = wq_select_unbound_cpu(raw_smp_processor_id());
@@ -1441,10 +1473,8 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
        /* pwq determined, queue */
        trace_workqueue_queue_work(req_cpu, pwq, work);
 
-       if (WARN_ON(!list_empty(&work->entry))) {
-               spin_unlock(&pwq->pool->lock);
-               return;
-       }
+       if (WARN_ON(!list_empty(&work->entry)))
+               goto out;
 
        pwq->nr_in_flight[pwq->work_color]++;
        work_flags = work_color_to_flags(pwq->work_color);
@@ -1462,7 +1492,9 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 
        insert_work(pwq, work, worklist, work_flags);
 
+out:
        spin_unlock(&pwq->pool->lock);
+       rcu_read_unlock();
 }
 
 /**
@@ -1482,14 +1514,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
        bool ret = false;
        unsigned long flags;
 
-       local_irq_save(flags);
+       local_lock_irqsave(pendingb_lock,flags);
 
        if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
                __queue_work(cpu, wq, work);
                ret = true;
        }
 
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pendingb_lock, flags);
        return ret;
 }
 EXPORT_SYMBOL(queue_work_on);
@@ -1498,8 +1530,11 @@ void delayed_work_timer_fn(unsigned long __data)
 {
        struct delayed_work *dwork = (struct delayed_work *)__data;
 
+       /* XXX */
+       /* local_lock(pendingb_lock); */
        /* should have been called from irqsafe timer with irq already off */
        __queue_work(dwork->cpu, dwork->wq, &dwork->work);
+       /* local_unlock(pendingb_lock); */
 }
 EXPORT_SYMBOL(delayed_work_timer_fn);
 
@@ -1555,14 +1590,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
        unsigned long flags;
 
        /* read the comment in __queue_work() */
-       local_irq_save(flags);
+       local_lock_irqsave(pendingb_lock, flags);
 
        if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
                __queue_delayed_work(cpu, wq, dwork, delay);
                ret = true;
        }
 
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pendingb_lock, flags);
        return ret;
 }
 EXPORT_SYMBOL(queue_delayed_work_on);
@@ -1597,7 +1632,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
 
        if (likely(ret >= 0)) {
                __queue_delayed_work(cpu, wq, dwork, delay);
-               local_irq_restore(flags);
+               local_unlock_irqrestore(pendingb_lock, flags);
        }
 
        /* -ENOENT from try_to_grab_pending() becomes %true */
@@ -1630,7 +1665,9 @@ static void worker_enter_idle(struct worker *worker)
        worker->last_active = jiffies;
 
        /* idle_list is LIFO */
+       rt_lock_idle_list(pool);
        list_add(&worker->entry, &pool->idle_list);
+       rt_unlock_idle_list(pool);
 
        if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
                mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
@@ -1663,7 +1700,9 @@ static void worker_leave_idle(struct worker *worker)
                return;
        worker_clr_flags(worker, WORKER_IDLE);
        pool->nr_idle--;
+       rt_lock_idle_list(pool);
        list_del_init(&worker->entry);
+       rt_unlock_idle_list(pool);
 }
 
 static struct worker *alloc_worker(int node)
@@ -1829,7 +1868,9 @@ static void destroy_worker(struct worker *worker)
        pool->nr_workers--;
        pool->nr_idle--;
 
+       rt_lock_idle_list(pool);
        list_del_init(&worker->entry);
+       rt_unlock_idle_list(pool);
        worker->flags |= WORKER_DIE;
        wake_up_process(worker->task);
 }
@@ -2815,14 +2856,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
 
        might_sleep();
 
-       local_irq_disable();
+       rcu_read_lock();
        pool = get_work_pool(work);
        if (!pool) {
-               local_irq_enable();
+               rcu_read_unlock();
                return false;
        }
 
-       spin_lock(&pool->lock);
+       spin_lock_irq(&pool->lock);
        /* see the comment in try_to_grab_pending() with the same code */
        pwq = get_work_pwq(work);
        if (pwq) {
@@ -2853,10 +2894,11 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
                lock_map_acquire(&pwq->wq->lockdep_map);
                lock_map_release(&pwq->wq->lockdep_map);
        }
-
+       rcu_read_unlock();
        return true;
 already_gone:
        spin_unlock_irq(&pool->lock);
+       rcu_read_unlock();
        return false;
 }
 
@@ -2946,7 +2988,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
 
        /* tell other tasks trying to grab @work to back off */
        mark_work_canceling(work);
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pendingb_lock, flags);
 
        /*
         * This allows canceling during early boot.  We know that @work
@@ -3007,10 +3049,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync);
  */
 bool flush_delayed_work(struct delayed_work *dwork)
 {
-       local_irq_disable();
+       local_lock_irq(pendingb_lock);
        if (del_timer_sync(&dwork->timer))
                __queue_work(dwork->cpu, dwork->wq, &dwork->work);
-       local_irq_enable();
+       local_unlock_irq(pendingb_lock);
        return flush_work(&dwork->work);
 }
 EXPORT_SYMBOL(flush_delayed_work);
@@ -3028,7 +3070,7 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork)
                return false;
 
        set_work_pool_and_clear_pending(work, get_work_pool_id(work));
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pendingb_lock, flags);
        return ret;
 }
 
@@ -3284,7 +3326,7 @@ static void rcu_free_pool(struct rcu_head *rcu)
  * put_unbound_pool - put a worker_pool
  * @pool: worker_pool to put
  *
- * Put @pool.  If its refcnt reaches zero, it gets destroyed in sched-RCU
+ * Put @pool.  If its refcnt reaches zero, it gets destroyed in RCU
  * safe manner.  get_unbound_pool() calls this function on its failure path
  * and this function should be able to release pools which went through,
  * successfully or not, init_worker_pool().
@@ -3338,8 +3380,8 @@ static void put_unbound_pool(struct worker_pool *pool)
        del_timer_sync(&pool->idle_timer);
        del_timer_sync(&pool->mayday_timer);
 
-       /* sched-RCU protected to allow dereferences from get_work_pool() */
-       call_rcu_sched(&pool->rcu, rcu_free_pool);
+       /* RCU protected to allow dereferences from get_work_pool() */
+       call_rcu(&pool->rcu, rcu_free_pool);
 }
 
 /**
@@ -3446,14 +3488,14 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
        put_unbound_pool(pool);
        mutex_unlock(&wq_pool_mutex);
 
-       call_rcu_sched(&pwq->rcu, rcu_free_pwq);
+       call_rcu(&pwq->rcu, rcu_free_pwq);
 
        /*
         * If we're the last pwq going away, @wq is already dead and no one
         * is gonna access it anymore.  Schedule RCU free.
         */
        if (is_last)
-               call_rcu_sched(&wq->rcu, rcu_free_wq);
+               call_rcu(&wq->rcu, rcu_free_wq);
 }
 
 /**
@@ -4128,7 +4170,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
                 * The base ref is never dropped on per-cpu pwqs.  Directly
                 * schedule RCU free.
                 */
-               call_rcu_sched(&wq->rcu, rcu_free_wq);
+               call_rcu(&wq->rcu, rcu_free_wq);
        } else {
                /*
                 * We're the sole accessor of @wq at this point.  Directly
@@ -4238,7 +4280,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
        struct pool_workqueue *pwq;
        bool ret;
 
-       rcu_read_lock_sched();
+       rcu_read_lock();
+       preempt_disable();
 
        if (cpu == WORK_CPU_UNBOUND)
                cpu = smp_processor_id();
@@ -4249,7 +4292,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
                pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
 
        ret = !list_empty(&pwq->delayed_works);
-       rcu_read_unlock_sched();
+       preempt_enable();
+       rcu_read_unlock();
 
        return ret;
 }
@@ -4275,15 +4319,15 @@ unsigned int work_busy(struct work_struct *work)
        if (work_pending(work))
                ret |= WORK_BUSY_PENDING;
 
-       local_irq_save(flags);
+       rcu_read_lock();
        pool = get_work_pool(work);
        if (pool) {
-               spin_lock(&pool->lock);
+               spin_lock_irqsave(&pool->lock, flags);
                if (find_worker_executing_work(pool, work))
                        ret |= WORK_BUSY_RUNNING;
-               spin_unlock(&pool->lock);
+               spin_unlock_irqrestore(&pool->lock, flags);
        }
-       local_irq_restore(flags);
+       rcu_read_unlock();
 
        return ret;
 }
@@ -4472,7 +4516,7 @@ void show_workqueue_state(void)
        unsigned long flags;
        int pi;
 
-       rcu_read_lock_sched();
+       rcu_read_lock();
 
        pr_info("Showing busy workqueues and worker pools:\n");
 
@@ -4537,7 +4581,7 @@ void show_workqueue_state(void)
                touch_nmi_watchdog();
        }
 
-       rcu_read_unlock_sched();
+       rcu_read_unlock();
 }
 
 /*
@@ -4898,16 +4942,16 @@ bool freeze_workqueues_busy(void)
                 * nr_active is monotonically decreasing.  It's safe
                 * to peek without lock.
                 */
-               rcu_read_lock_sched();
+               rcu_read_lock();
                for_each_pwq(pwq, wq) {
                        WARN_ON_ONCE(pwq->nr_active < 0);
                        if (pwq->nr_active) {
                                busy = true;
-                               rcu_read_unlock_sched();
+                               rcu_read_unlock();
                                goto out_unlock;
                        }
                }
-               rcu_read_unlock_sched();
+               rcu_read_unlock();
        }
 out_unlock:
        mutex_unlock(&wq_pool_mutex);
@@ -5097,7 +5141,8 @@ static ssize_t wq_pool_ids_show(struct device *dev,
        const char *delim = "";
        int node, written = 0;
 
-       rcu_read_lock_sched();
+       get_online_cpus();
+       rcu_read_lock();
        for_each_node(node) {
                written += scnprintf(buf + written, PAGE_SIZE - written,
                                     "%s%d:%d", delim, node,
@@ -5105,7 +5150,8 @@ static ssize_t wq_pool_ids_show(struct device *dev,
                delim = " ";
        }
        written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
-       rcu_read_unlock_sched();
+       rcu_read_unlock();
+       put_online_cpus();
 
        return written;
 }
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index d390d1be3748..2dbcfe9bc364 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -45,6 +45,7 @@ struct worker {
        unsigned long           last_active;    /* L: last active timestamp */
        unsigned int            flags;          /* X: flags */
        int                     id;             /* I: worker id */
+       int                     sleeping;       /* None */
 
        /*
         * Opaque string set with work_set_desc().  Printed out with task
@@ -70,7 +71,7 @@ static inline struct worker *current_wq_worker(void)
  * Scheduler hooks for concurrency managed workqueue.  Only to be used from
  * sched/core.c and workqueue.c.
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task);
+void wq_worker_running(struct task_struct *task);
+void wq_worker_sleeping(struct task_struct *task);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index b1445b22a6de..9ab51b78991a 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -428,6 +428,7 @@ config CHECK_SIGNATURE
 
 config CPUMASK_OFFSTACK
        bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+       depends on !PREEMPT_RT_FULL
        help
          Use dynamic allocation for cpumask_var_t, instead of putting
          them on the stack.  This is a bit more expensive, but avoids
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 62d0e25c054c..401b7ed164b5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1197,7 +1197,7 @@ config DEBUG_ATOMIC_SLEEP
 
 config DEBUG_LOCKING_API_SELFTESTS
        bool "Locking API boot-time self-tests"
-       depends on DEBUG_KERNEL
+       depends on DEBUG_KERNEL && !PREEMPT_RT_FULL
        help
          Say Y here if you want the kernel to run a short self-test during
          bootup. The self-test checks whether common types of locking bugs
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 99308479b1c8..161da6c6e173 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -339,7 +339,10 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
        struct debug_obj *obj;
        unsigned long flags;
 
-       fill_pool();
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (preempt_count() == 0 && !irqs_disabled())
+#endif
+               fill_pool();
 
        db = get_bucket((unsigned long) addr);
 
diff --git a/lib/irq_poll.c b/lib/irq_poll.c
index 86a709954f5a..9c069ef83d6d 100644
--- a/lib/irq_poll.c
+++ b/lib/irq_poll.c
@@ -37,6 +37,7 @@ void irq_poll_sched(struct irq_poll *iop)
        list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
        __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(irq_poll_sched);
 
@@ -72,6 +73,7 @@ void irq_poll_complete(struct irq_poll *iop)
        local_irq_save(flags);
        __irq_poll_complete(iop);
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(irq_poll_complete);
 
@@ -96,6 +98,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
                }
 
                local_irq_enable();
+               preempt_check_resched_rt();
 
                /* Even though interrupts have been re-enabled, this
                 * access is safe because interrupts can only add new
@@ -133,6 +136,7 @@ static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
                __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
 
        local_irq_enable();
+       preempt_check_resched_rt();
 }
 
 /**
@@ -196,6 +200,7 @@ static int irq_poll_cpu_dead(unsigned int cpu)
                         this_cpu_ptr(&blk_cpu_iopoll));
        __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
        local_irq_enable();
+       preempt_check_resched_rt();
 
        return 0;
 }
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index b5c1293ce147..075e225f4111 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -742,6 +742,8 @@ GENERATE_TESTCASE(init_held_rtmutex);
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock)
 
@@ -757,9 +759,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Enabling hardirqs with a softirq-safe lock held:
  */
@@ -792,6 +797,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
 #undef E1
 #undef E2
 
+#endif
+
 /*
  * Enabling irqs with an irq-safe lock held:
  */
@@ -815,6 +822,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock)
 
@@ -830,6 +839,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
@@ -861,6 +872,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock)
 
@@ -876,6 +889,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3
@@ -909,6 +924,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock)
 
@@ -924,10 +941,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * read-lock / write-lock irq inversion.
  *
@@ -990,6 +1011,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_wlock)
 #undef E2
 #undef E3
 
+#endif
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * read-lock / write-lock recursion that is actually safe.
  */
@@ -1028,6 +1053,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft)
 #undef E2
 #undef E3
 
+#endif
+
 /*
  * read-lock / write-lock recursion that is unsafe.
  */
@@ -2057,6 +2084,7 @@ void locking_selftest(void)
 
        printk("  --------------------------------------------------------------------------\n");
 
+#ifndef CONFIG_PREEMPT_RT_FULL
        /*
         * irq-context testcases:
         */
@@ -2069,6 +2097,28 @@ void locking_selftest(void)
 
        DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion);
 //     DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2);
+#else
+       /* On -rt, we only do hardirq context test for raw spinlock */
+       DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12);
+       DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21);
+
+       DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12);
+       DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21);
+
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321);
+
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312);
+       DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321);
+#endif
 
        ww_tests();
 
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 6016f1deb1f5..cdd43086b55b 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -27,6 +27,9 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/percpu_ida.h>
+#include <linux/locallock.h>
+
+static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock);
 
 struct percpu_ida_cpu {
        /*
@@ -149,13 +152,13 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
        unsigned long flags;
        int tag;
 
-       local_irq_save(flags);
+       local_lock_irqsave(irq_off_lock, flags);
        tags = this_cpu_ptr(pool->tag_cpu);
 
        /* Fastpath */
        tag = alloc_local_tag(tags);
        if (likely(tag >= 0)) {
-               local_irq_restore(flags);
+               local_unlock_irqrestore(irq_off_lock, flags);
                return tag;
        }
 
@@ -174,6 +177,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 
                if (!tags->nr_free)
                        alloc_global_tags(pool, tags);
+
                if (!tags->nr_free)
                        steal_tags(pool, tags);
 
@@ -185,7 +189,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
                }
 
                spin_unlock(&pool->lock);
-               local_irq_restore(flags);
+               local_unlock_irqrestore(irq_off_lock, flags);
 
                if (tag >= 0 || state == TASK_RUNNING)
                        break;
@@ -197,7 +201,7 @@ int percpu_ida_alloc(struct percpu_ida *pool, int state)
 
                schedule();
 
-               local_irq_save(flags);
+               local_lock_irqsave(irq_off_lock, flags);
                tags = this_cpu_ptr(pool->tag_cpu);
        }
        if (state != TASK_RUNNING)
@@ -222,7 +226,7 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
 
        BUG_ON(tag >= pool->nr_tags);
 
-       local_irq_save(flags);
+       local_lock_irqsave(irq_off_lock, flags);
        tags = this_cpu_ptr(pool->tag_cpu);
 
        spin_lock(&tags->lock);
@@ -254,7 +258,7 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
                spin_unlock(&pool->lock);
        }
 
-       local_irq_restore(flags);
+       local_unlock_irqrestore(irq_off_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ida_free);
 
@@ -346,7 +350,7 @@ int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
        struct percpu_ida_cpu *remote;
        unsigned cpu, i, err = 0;
 
-       local_irq_save(flags);
+       local_lock_irqsave(irq_off_lock, flags);
        for_each_possible_cpu(cpu) {
                remote = per_cpu_ptr(pool->tag_cpu, cpu);
                spin_lock(&remote->lock);
@@ -368,7 +372,7 @@ int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
        }
        spin_unlock(&pool->lock);
 out:
-       local_irq_restore(flags);
+       local_unlock_irqrestore(irq_off_lock, flags);
        return err;
 }
 EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d172f0341b80..c1da1109a107 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -37,7 +37,7 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-
+#include <linux/locallock.h>
 
 /* Number of nodes in fully populated tree of given height */
 static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly;
@@ -86,6 +86,7 @@ struct radix_tree_preload {
        struct radix_tree_node *nodes;
 };
 static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
+static DEFINE_LOCAL_IRQ_LOCK(radix_tree_preloads_lock);
 
 static inline struct radix_tree_node *entry_to_node(void *ptr)
 {
@@ -404,12 +405,13 @@ radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent,
                 * succeed in getting a node here (and never reach
                 * kmem_cache_alloc)
                 */
-               rtp = this_cpu_ptr(&radix_tree_preloads);
+               rtp = &get_locked_var(radix_tree_preloads_lock, radix_tree_preloads);
                if (rtp->nr) {
                        ret = rtp->nodes;
                        rtp->nodes = ret->parent;
                        rtp->nr--;
                }
+               put_locked_var(radix_tree_preloads_lock, radix_tree_preloads);
                /*
                 * Update the allocation stack trace as this is more useful
                 * for debugging.
@@ -475,14 +477,14 @@ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
         */
        gfp_mask &= ~__GFP_ACCOUNT;
 
-       preempt_disable();
+       local_lock(radix_tree_preloads_lock);
        rtp = this_cpu_ptr(&radix_tree_preloads);
        while (rtp->nr < nr) {
-               preempt_enable();
+               local_unlock(radix_tree_preloads_lock);
                node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
                if (node == NULL)
                        goto out;
-               preempt_disable();
+               local_lock(radix_tree_preloads_lock);
                rtp = this_cpu_ptr(&radix_tree_preloads);
                if (rtp->nr < nr) {
                        node->parent = rtp->nodes;
@@ -524,7 +526,7 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
        if (gfpflags_allow_blocking(gfp_mask))
                return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE);
        /* Preloading doesn't help anything with this gfp mask, skip it */
-       preempt_disable();
+       local_lock(radix_tree_preloads_lock);
        return 0;
 }
 EXPORT_SYMBOL(radix_tree_maybe_preload);
@@ -562,7 +564,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order)
 
        /* Preloading doesn't help anything with this gfp mask, skip it */
        if (!gfpflags_allow_blocking(gfp_mask)) {
-               preempt_disable();
+               local_lock(radix_tree_preloads_lock);
                return 0;
        }
 
@@ -596,6 +598,12 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order)
        return __radix_tree_preload(gfp_mask, nr_nodes);
 }
 
+void radix_tree_preload_end(void)
+{
+       local_unlock(radix_tree_preloads_lock);
+}
+EXPORT_SYMBOL(radix_tree_preload_end);
+
 static unsigned radix_tree_load_root(const struct radix_tree_root *root,
                struct radix_tree_node **nodep, unsigned long *maxindex)
 {
@@ -2105,10 +2113,16 @@ EXPORT_SYMBOL(radix_tree_tagged);
 void idr_preload(gfp_t gfp_mask)
 {
        if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE))
-               preempt_disable();
+               local_lock(radix_tree_preloads_lock);
 }
 EXPORT_SYMBOL(idr_preload);
 
+void idr_preload_end(void)
+{
+       local_unlock(radix_tree_preloads_lock);
+}
+EXPORT_SYMBOL(idr_preload_end);
+
 /**
  * ida_pre_get - reserve resources for ida allocation
  * @ida: ida handle
@@ -2125,7 +2139,7 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
         * to return to the ida_pre_get() step.
         */
        if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE))
-               preempt_enable();
+               local_unlock(radix_tree_preloads_lock);
 
        if (!this_cpu_read(ida_bitmap)) {
                struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index be7b4dd6b68d..d06c15d3d186 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -620,7 +620,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
                        flush_kernel_dcache_page(miter->page);
 
                if (miter->__flags & SG_MITER_ATOMIC) {
-                       WARN_ON_ONCE(preemptible());
+                       WARN_ON_ONCE(!pagefault_disabled());
                        kunmap_atomic(miter->addr);
                } else
                        kunmap(miter->page);
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 835cc6df2776..6f4a4ae881c8 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -23,7 +23,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1,
         * Kernel threads bound to a single CPU can safely use
         * smp_processor_id():
         */
-       if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
+       if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu)))
                goto out;
 
        /*
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index 4a720ed4fdaf..0d54bcbc8170 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -33,8 +33,9 @@
  * @head: head of timerqueue
  * @node: timer node to be added
  *
- * Adds the timer node to the timerqueue, sorted by the
- * node's expires value.
+ * Adds the timer node to the timerqueue, sorted by the node's expires
+ * value. Returns true if the newly added timer is the first expiring timer in
+ * the queue.
  */
 bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 {
@@ -70,7 +71,8 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
  * @head: head of timerqueue
  * @node: timer node to be removed
  *
- * Removes the timer node from the timerqueue.
+ * Removes the timer node from the timerqueue. Returns true if the queue is
+ * not empty after the remove.
  */
 bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 {
diff --git a/localversion-rt b/localversion-rt
new file mode 100644
index 000000000000..8a777ac42aab
--- /dev/null
+++ b/localversion-rt
@@ -0,0 +1 @@
+-rt47
diff --git a/mm/Kconfig b/mm/Kconfig
index 59efbd3337e0..3df123c0bc3f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -385,7 +385,7 @@ config NOMMU_INITIAL_TRIM_EXCESS
 
 config TRANSPARENT_HUGEPAGE
        bool "Transparent Hugepage Support"
-       depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
+       depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL
        select COMPACTION
        select RADIX_TREE_MULTIORDER
        help
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 9386c98dac12..5e9d804c37cb 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -470,9 +470,9 @@ void wb_congested_put(struct bdi_writeback_congested *congested)
 {
        unsigned long flags;
 
-       local_irq_save(flags);
+       local_irq_save_nort(flags);
        if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) {
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
                return;
        }
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 85395dc6eb13..d6c8ed009e93 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1634,10 +1634,12 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
                                block_start_pfn(cc->migrate_pfn, cc->order);
 
                        if (cc->last_migrated_pfn < current_block_start) {
-                               cpu = get_cpu();
+                               cpu = get_cpu_light();
+                               local_lock_irq(swapvec_lock);
                                lru_add_drain_cpu(cpu);
+                               local_unlock_irq(swapvec_lock);
                                drain_local_pages(zone);
-                               put_cpu();
+                               put_cpu_light();
                                /* No more flushing until we migrate again */
                                cc->last_migrated_pfn = 0;
                        }
diff --git a/mm/filemap.c b/mm/filemap.c
index e2e738cc08b1..c47070dae8b9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -110,6 +110,7 @@
  * ->i_mmap_rwsem
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
+DECLARE_LOCAL_IRQ_LOCK(shadow_nodes_lock);
 
 static int page_cache_tree_insert(struct address_space *mapping,
                                  struct page *page, void **shadowp)
@@ -133,8 +134,10 @@ static int page_cache_tree_insert(struct address_space *mapping,
                if (shadowp)
                        *shadowp = p;
        }
+       local_lock(shadow_nodes_lock);
        __radix_tree_replace(&mapping->page_tree, node, slot, page,
-                            workingset_update_node, mapping);
+                            __workingset_update_node, mapping);
+       local_unlock(shadow_nodes_lock);
        mapping->nrpages++;
        return 0;
 }
@@ -151,6 +154,7 @@ static void page_cache_tree_delete(struct address_space *mapping,
        VM_BUG_ON_PAGE(PageTail(page), page);
        VM_BUG_ON_PAGE(nr != 1 && shadow, page);
 
+       local_lock(shadow_nodes_lock);
        for (i = 0; i < nr; i++) {
                struct radix_tree_node *node;
                void **slot;
@@ -162,8 +166,9 @@ static void page_cache_tree_delete(struct address_space *mapping,
 
                radix_tree_clear_tags(&mapping->page_tree, node, slot);
                __radix_tree_replace(&mapping->page_tree, node, slot, shadow,
-                                    workingset_update_node, mapping);
+                                    __workingset_update_node, mapping);
        }
+       local_unlock(shadow_nodes_lock);
 
        if (shadow) {
                mapping->nrexceptional += nr;
diff --git a/mm/highmem.c b/mm/highmem.c
index 59db3223a5d6..22aa3ddbd87b 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -30,10 +30,11 @@
 #include <linux/kgdb.h>
 #include <asm/tlbflush.h>
 
-
+#ifndef CONFIG_PREEMPT_RT_FULL
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
 DEFINE_PER_CPU(int, __kmap_atomic_idx);
 #endif
+#endif
 
 /*
  * Virtual_count is not a pure "count".
@@ -108,8 +109,9 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
 unsigned long totalhigh_pages __read_mostly;
 EXPORT_SYMBOL(totalhigh_pages);
 
-
+#ifndef CONFIG_PREEMPT_RT_FULL
 EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
+#endif
 
 unsigned int nr_free_highpages (void)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6a9a7e1066ef..3cc297730103 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -69,6 +69,7 @@
 #include <net/sock.h>
 #include <net/ip.h>
 #include "slab.h"
+#include <linux/locallock.h>
 
 #include <linux/uaccess.h>
 
@@ -94,6 +95,8 @@ int do_swap_account __read_mostly;
 #define do_swap_account                0
 #endif
 
+static DEFINE_LOCAL_IRQ_LOCK(event_lock);
+
 /* Whether legacy memory+swap accounting is active */
 static bool do_memsw_account(void)
 {
@@ -1831,7 +1834,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
         * as well as workers from this path always operate on the local
         * per-cpu data. CPU up doesn't touch memcg_stock at all.
         */
-       curcpu = get_cpu();
+       curcpu = get_cpu_light();
        for_each_online_cpu(cpu) {
                struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
                struct mem_cgroup *memcg;
@@ -1851,7 +1854,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
                }
                css_put(&memcg->css);
        }
-       put_cpu();
+       put_cpu_light();
        mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -4631,12 +4634,12 @@ static int mem_cgroup_move_account(struct page *page,
 
        ret = 0;
 
-       local_irq_disable();
+       local_lock_irq(event_lock);
        mem_cgroup_charge_statistics(to, page, compound, nr_pages);
        memcg_check_events(to, page);
        mem_cgroup_charge_statistics(from, page, compound, -nr_pages);
        memcg_check_events(from, page);
-       local_irq_enable();
+       local_unlock_irq(event_lock);
 out_unlock:
        unlock_page(page);
 out:
@@ -5579,10 +5582,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 
        commit_charge(page, memcg, lrucare);
 
-       local_irq_disable();
+       local_lock_irq(event_lock);
        mem_cgroup_charge_statistics(memcg, page, compound, nr_pages);
        memcg_check_events(memcg, page);
-       local_irq_enable();
+       local_unlock_irq(event_lock);
 
        if (do_memsw_account() && PageSwapCache(page)) {
                swp_entry_t entry = { .val = page_private(page) };
@@ -5651,7 +5654,7 @@ static void uncharge_batch(const struct uncharge_gather *ug)
                memcg_oom_recover(ug->memcg);
        }
 
-       local_irq_save(flags);
+       local_lock_irqsave(event_lock, flags);
        __this_cpu_sub(ug->memcg->stat->count[MEMCG_RSS], ug->nr_anon);
        __this_cpu_sub(ug->memcg->stat->count[MEMCG_CACHE], ug->nr_file);
        __this_cpu_sub(ug->memcg->stat->count[MEMCG_RSS_HUGE], ug->nr_huge);
@@ -5659,7 +5662,7 @@ static void uncharge_batch(const struct uncharge_gather *ug)
        __this_cpu_add(ug->memcg->stat->events[PGPGOUT], ug->pgpgout);
        __this_cpu_add(ug->memcg->stat->nr_page_events, nr_pages);
        memcg_check_events(ug->memcg, ug->dummy_page);
-       local_irq_restore(flags);
+       local_unlock_irqrestore(event_lock, flags);
 
        if (!mem_cgroup_is_root(ug->memcg))
                css_put_many(&ug->memcg->css, nr_pages);
@@ -5822,10 +5825,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 
        commit_charge(newpage, memcg, false);
 
-       local_irq_save(flags);
+       local_lock_irqsave(event_lock, flags);
        mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
        memcg_check_events(memcg, newpage);
-       local_irq_restore(flags);
+       local_unlock_irqrestore(event_lock, flags);
 }
 
 DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
@@ -6017,6 +6020,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
        struct mem_cgroup *memcg, *swap_memcg;
        unsigned int nr_entries;
        unsigned short oldid;
+       unsigned long flags;
 
        VM_BUG_ON_PAGE(PageLRU(page), page);
        VM_BUG_ON_PAGE(page_count(page), page);
@@ -6062,13 +6066,17 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
         * important here to have the interrupts disabled because it is the
         * only synchronisation we have for udpating the per-CPU variables.
         */
+       local_lock_irqsave(event_lock, flags);
+#ifndef CONFIG_PREEMPT_RT_BASE
        VM_BUG_ON(!irqs_disabled());
+#endif
        mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page),
                                     -nr_entries);
        memcg_check_events(memcg, page);
 
        if (!mem_cgroup_is_root(memcg))
                css_put_many(&memcg->css, nr_entries);
+       local_unlock_irqrestore(event_lock, flags);
 }
 
 /**
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index 3e612ae748e9..d0ccc070979f 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -25,6 +25,7 @@ void use_mm(struct mm_struct *mm)
        struct task_struct *tsk = current;
 
        task_lock(tsk);
+       preempt_disable_rt();
        active_mm = tsk->active_mm;
        if (active_mm != mm) {
                mmgrab(mm);
@@ -32,6 +33,7 @@ void use_mm(struct mm_struct *mm)
        }
        tsk->mm = mm;
        switch_mm(active_mm, mm, tsk);
+       preempt_enable_rt();
        task_unlock(tsk);
 #ifdef finish_arch_post_lock_switch
        finish_arch_post_lock_switch();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a604b5da6755..525a6f2d5144 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -61,6 +61,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/mm.h>
+#include <linux/locallock.h>
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
@@ -286,6 +287,18 @@ EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
+static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define cpu_lock_irqsave(cpu, flags)          \
+       local_lock_irqsave_on(pa_lock, flags, cpu)
+# define cpu_unlock_irqrestore(cpu, flags)     \
+       local_unlock_irqrestore_on(pa_lock, flags, cpu)
+#else
+# define cpu_lock_irqsave(cpu, flags)          local_irq_save(flags)
+# define cpu_unlock_irqrestore(cpu, flags)     local_irq_restore(flags)
+#endif
+
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -1094,7 +1107,7 @@ static bool bulkfree_pcp_prepare(struct page *page)
 #endif /* CONFIG_DEBUG_VM */
 
 /*
- * Frees a number of pages from the PCP lists
+ * Frees a number of pages which have been collected from the pcp lists.
  * Assumes all pages on list are in same zone, and of same order.
  * count is the number of pages to free.
  *
@@ -1105,15 +1118,53 @@ static bool bulkfree_pcp_prepare(struct page *page)
  * pinned" detection logic.
  */
 static void free_pcppages_bulk(struct zone *zone, int count,
-                                       struct per_cpu_pages *pcp)
+                              struct list_head *list)
 {
-       int migratetype = 0;
-       int batch_free = 0;
        bool isolated_pageblocks;
+       unsigned long flags;
 
-       spin_lock(&zone->lock);
+       spin_lock_irqsave(&zone->lock, flags);
        isolated_pageblocks = has_isolate_pageblock(zone);
 
+       while (!list_empty(list)) {
+               struct page *page;
+               int mt; /* migratetype of the to-be-freed page */
+
+               page = list_first_entry(list, struct page, lru);
+               /* must delete as __free_one_page list manipulates */
+               list_del(&page->lru);
+
+               mt = get_pcppage_migratetype(page);
+               /* MIGRATE_ISOLATE page should not go to pcplists */
+               VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+               /* Pageblock could have been isolated meanwhile */
+               if (unlikely(isolated_pageblocks))
+                       mt = get_pageblock_migratetype(page);
+
+               if (bulkfree_pcp_prepare(page))
+                       continue;
+
+               __free_one_page(page, page_to_pfn(page), zone, 0, mt);
+               trace_mm_page_pcpu_drain(page, 0, mt);
+               count--;
+       }
+       WARN_ON(count != 0);
+       spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+/*
+ * Moves a number of pages from the PCP lists to free list which
+ * is freed outside of the locked region.
+ *
+ * Assumes all pages on list are in same zone, and of same order.
+ * count is the number of pages to free.
+ */
+static void isolate_pcp_pages(int count, struct per_cpu_pages *src,
+                             struct list_head *dst)
+{
+       int migratetype = 0;
+       int batch_free = 0;
+
        while (count) {
                struct page *page;
                struct list_head *list;
@@ -1129,7 +1180,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
                        batch_free++;
                        if (++migratetype == MIGRATE_PCPTYPES)
                                migratetype = 0;
-                       list = &pcp->lists[migratetype];
+                       list = &src->lists[migratetype];
                } while (list_empty(list));
 
                /* This is the only non-empty list. Free them all. */
@@ -1137,27 +1188,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
                        batch_free = count;
 
                do {
-                       int mt; /* migratetype of the to-be-freed page */
-
                        page = list_last_entry(list, struct page, lru);
-                       /* must delete as __free_one_page list manipulates */
                        list_del(&page->lru);
 
-                       mt = get_pcppage_migratetype(page);
-                       /* MIGRATE_ISOLATE page should not go to pcplists */
-                       VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
-                       /* Pageblock could have been isolated meanwhile */
-                       if (unlikely(isolated_pageblocks))
-                               mt = get_pageblock_migratetype(page);
-
-                       if (bulkfree_pcp_prepare(page))
-                               continue;
-
-                       __free_one_page(page, page_to_pfn(page), zone, 0, mt);
-                       trace_mm_page_pcpu_drain(page, 0, mt);
+                       list_add(&page->lru, dst);
                } while (--count && --batch_free && !list_empty(list));
        }
-       spin_unlock(&zone->lock);
 }
 
 static void free_one_page(struct zone *zone,
@@ -1165,13 +1201,15 @@ static void free_one_page(struct zone *zone,
                                unsigned int order,
                                int migratetype)
 {
-       spin_lock(&zone->lock);
+       unsigned long flags;
+
+       spin_lock_irqsave(&zone->lock, flags);
        if (unlikely(has_isolate_pageblock(zone) ||
                is_migrate_isolate(migratetype))) {
                migratetype = get_pfnblock_migratetype(page, pfn);
        }
        __free_one_page(page, pfn, zone, order, migratetype);
-       spin_unlock(&zone->lock);
+       spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
@@ -1257,10 +1295,10 @@ static void __free_pages_ok(struct page *page, unsigned int order)
                return;
 
        migratetype = get_pfnblock_migratetype(page, pfn);
-       local_irq_save(flags);
+       local_lock_irqsave(pa_lock, flags);
        __count_vm_events(PGFREE, 1 << order);
        free_one_page(page_zone(page), page, pfn, order, migratetype);
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
 }
 
 static void __init __free_pages_boot_core(struct page *page, unsigned int order)
@@ -2378,16 +2416,18 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
        unsigned long flags;
+       LIST_HEAD(dst);
        int to_drain, batch;
 
-       local_irq_save(flags);
+       local_lock_irqsave(pa_lock, flags);
        batch = READ_ONCE(pcp->batch);
        to_drain = min(pcp->count, batch);
        if (to_drain > 0) {
-               free_pcppages_bulk(zone, to_drain, pcp);
+               isolate_pcp_pages(to_drain, pcp, &dst);
                pcp->count -= to_drain;
        }
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
+       free_pcppages_bulk(zone, to_drain, &dst);
 }
 #endif
 
@@ -2403,16 +2443,21 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
        unsigned long flags;
        struct per_cpu_pageset *pset;
        struct per_cpu_pages *pcp;
+       LIST_HEAD(dst);
+       int count;
 
-       local_irq_save(flags);
+       cpu_lock_irqsave(cpu, flags);
        pset = per_cpu_ptr(zone->pageset, cpu);
 
        pcp = &pset->pcp;
-       if (pcp->count) {
-               free_pcppages_bulk(zone, pcp->count, pcp);
+       count = pcp->count;
+       if (count) {
+               isolate_pcp_pages(count, pcp, &dst);
                pcp->count = 0;
        }
-       local_irq_restore(flags);
+       cpu_unlock_irqrestore(cpu, flags);
+       if (count)
+               free_pcppages_bulk(zone, count, &dst);
 }
 
 /*
@@ -2447,6 +2492,7 @@ void drain_local_pages(struct zone *zone)
                drain_pages(cpu);
 }
 
+#ifndef CONFIG_PREEMPT_RT_BASE
 static void drain_local_pages_wq(struct work_struct *work)
 {
        /*
@@ -2460,6 +2506,7 @@ static void drain_local_pages_wq(struct work_struct *work)
        drain_local_pages(NULL);
        preempt_enable();
 }
+#endif
 
 /*
  * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
@@ -2526,7 +2573,14 @@ void drain_all_pages(struct zone *zone)
                else
                        cpumask_clear_cpu(cpu, &cpus_with_pcps);
        }
-
+#ifdef CONFIG_PREEMPT_RT_BASE
+       for_each_cpu(cpu, &cpus_with_pcps) {
+               if (zone)
+                       drain_pages_zone(cpu, zone);
+               else
+                       drain_pages(cpu);
+       }
+#else
        for_each_cpu(cpu, &cpus_with_pcps) {
                struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
                INIT_WORK(work, drain_local_pages_wq);
@@ -2534,6 +2588,7 @@ void drain_all_pages(struct zone *zone)
        }
        for_each_cpu(cpu, &cpus_with_pcps)
                flush_work(per_cpu_ptr(&pcpu_drain, cpu));
+#endif
 
        mutex_unlock(&pcpu_drain_mutex);
 }
@@ -2610,7 +2665,7 @@ void free_hot_cold_page(struct page *page, bool cold)
 
        migratetype = get_pfnblock_migratetype(page, pfn);
        set_pcppage_migratetype(page, migratetype);
-       local_irq_save(flags);
+       local_lock_irqsave(pa_lock, flags);
        __count_vm_event(PGFREE);
 
        /*
@@ -2636,12 +2691,17 @@ void free_hot_cold_page(struct page *page, bool cold)
        pcp->count++;
        if (pcp->count >= pcp->high) {
                unsigned long batch = READ_ONCE(pcp->batch);
-               free_pcppages_bulk(zone, batch, pcp);
+               LIST_HEAD(dst);
+
+               isolate_pcp_pages(batch, pcp, &dst);
                pcp->count -= batch;
+               local_unlock_irqrestore(pa_lock, flags);
+               free_pcppages_bulk(zone, batch, &dst);
+               return;
        }
 
 out:
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
 }
 
 /*
@@ -2789,7 +2849,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
        struct page *page;
        unsigned long flags;
 
-       local_irq_save(flags);
+       local_lock_irqsave(pa_lock, flags);
        pcp = &this_cpu_ptr(zone->pageset)->pcp;
        list = &pcp->lists[migratetype];
        page = __rmqueue_pcplist(zone,  migratetype, cold, pcp, list);
@@ -2797,7 +2857,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
                __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
                zone_statistics(preferred_zone, zone);
        }
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
        return page;
 }
 
@@ -2824,7 +2884,7 @@ struct page *rmqueue(struct zone *preferred_zone,
         * allocate greater than order-1 page units with __GFP_NOFAIL.
         */
        WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
-       spin_lock_irqsave(&zone->lock, flags);
+       local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
 
        do {
                page = NULL;
@@ -2844,14 +2904,14 @@ struct page *rmqueue(struct zone *preferred_zone,
 
        __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
        zone_statistics(preferred_zone, zone);
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
 
 out:
        VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
        return page;
 
 failed:
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
        return NULL;
 }
 
@@ -6785,8 +6845,9 @@ void __init free_area_init(unsigned long *zones_size)
 
 static int page_alloc_cpu_dead(unsigned int cpu)
 {
-
+       local_lock_irq_on(swapvec_lock, cpu);
        lru_add_drain_cpu(cpu);
+       local_unlock_irq_on(swapvec_lock, cpu);
        drain_pages(cpu);
 
        /*
@@ -7690,7 +7751,7 @@ void zone_pcp_reset(struct zone *zone)
        struct per_cpu_pageset *pset;
 
        /* avoid races with drain_pages()  */
-       local_irq_save(flags);
+       local_lock_irqsave(pa_lock, flags);
        if (zone->pageset != &boot_pageset) {
                for_each_online_cpu(cpu) {
                        pset = per_cpu_ptr(zone->pageset, cpu);
@@ -7699,7 +7760,7 @@ void zone_pcp_reset(struct zone *zone)
                free_percpu(zone->pageset);
                zone->pageset = &boot_pageset;
        }
-       local_irq_restore(flags);
+       local_unlock_irqrestore(pa_lock, flags);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
diff --git a/mm/slab.h b/mm/slab.h
index 485d9fbb8802..f3b06c48bf39 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -451,7 +451,11 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
  * The slab lists for all objects.
  */
 struct kmem_cache_node {
+#ifdef CONFIG_SLUB
+       raw_spinlock_t list_lock;
+#else
        spinlock_t list_lock;
+#endif
 
 #ifdef CONFIG_SLAB
        struct list_head slabs_partial; /* partial list first, better asm code */
diff --git a/mm/slub.c b/mm/slub.c
index 220d42e592ef..9b337c28dd1f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1179,7 +1179,7 @@ static noinline int free_debug_processing(
        unsigned long uninitialized_var(flags);
        int ret = 0;
 
-       spin_lock_irqsave(&n->list_lock, flags);
+       raw_spin_lock_irqsave(&n->list_lock, flags);
        slab_lock(page);
 
        if (s->flags & SLAB_CONSISTENCY_CHECKS) {
@@ -1214,7 +1214,7 @@ static noinline int free_debug_processing(
                         bulk_cnt, cnt);
 
        slab_unlock(page);
-       spin_unlock_irqrestore(&n->list_lock, flags);
+       raw_spin_unlock_irqrestore(&n->list_lock, flags);
        if (!ret)
                slab_fix(s, "Object at 0x%p not freed", object);
        return ret;
@@ -1342,6 +1342,12 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 
 #endif /* CONFIG_SLUB_DEBUG */
 
+struct slub_free_list {
+       raw_spinlock_t          lock;
+       struct list_head        list;
+};
+static DEFINE_PER_CPU(struct slub_free_list, slub_free_list);
+
 /*
  * Hooks for other subsystems that check memory allocations. In a typical
  * production configuration these hooks all should produce no code at all.
@@ -1561,10 +1567,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
        void *start, *p;
        int idx, order;
        bool shuffle;
+       bool enableirqs = false;
 
        flags &= gfp_allowed_mask;
 
        if (gfpflags_allow_blocking(flags))
+               enableirqs = true;
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (system_state > SYSTEM_BOOTING)
+               enableirqs = true;
+#endif
+       if (enableirqs)
                local_irq_enable();
 
        flags |= s->allocflags;
@@ -1623,7 +1636,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
        page->frozen = 1;
 
 out:
-       if (gfpflags_allow_blocking(flags))
+       if (enableirqs)
                local_irq_disable();
        if (!page)
                return NULL;
@@ -1681,6 +1694,16 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
        __free_pages(page, order);
 }
 
+static void free_delayed(struct list_head *h)
+{
+       while(!list_empty(h)) {
+               struct page *page = list_first_entry(h, struct page, lru);
+
+               list_del(&page->lru);
+               __free_slab(page->slab_cache, page);
+       }
+}
+
 #define need_reserve_slab_rcu                                          \
        (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head))
 
@@ -1712,6 +1735,12 @@ static void free_slab(struct kmem_cache *s, struct page *page)
                }
 
                call_rcu(head, rcu_free_slab);
+       } else if (irqs_disabled()) {
+               struct slub_free_list *f = this_cpu_ptr(&slub_free_list);
+
+               raw_spin_lock(&f->lock);
+               list_add(&page->lru, &f->list);
+               raw_spin_unlock(&f->lock);
        } else
                __free_slab(s, page);
 }
@@ -1819,7 +1848,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
        if (!n || !n->nr_partial)
                return NULL;
 
-       spin_lock(&n->list_lock);
+       raw_spin_lock(&n->list_lock);
        list_for_each_entry_safe(page, page2, &n->partial, lru) {
                void *t;
 
@@ -1844,7 +1873,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
                        break;
 
        }
-       spin_unlock(&n->list_lock);
+       raw_spin_unlock(&n->list_lock);
        return object;
 }
 
@@ -2090,7 +2119,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
                         * that acquire_slab() will see a slab page that
                         * is frozen
                         */
-                       spin_lock(&n->list_lock);
+                       raw_spin_lock(&n->list_lock);
                }
        } else {
                m = M_FULL;
@@ -2101,7 +2130,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
                         * slabs from diagnostic functions will not see
                         * any frozen slabs.
                         */
-                       spin_lock(&n->list_lock);
+                       raw_spin_lock(&n->list_lock);
                }
        }
 
@@ -2136,7 +2165,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
                goto redo;
 
        if (lock)
-               spin_unlock(&n->list_lock);
+               raw_spin_unlock(&n->list_lock);
 
        if (m == M_FREE) {
                stat(s, DEACTIVATE_EMPTY);
@@ -2171,10 +2200,10 @@ static void unfreeze_partials(struct kmem_cache *s,
                n2 = get_node(s, page_to_nid(page));
                if (n != n2) {
                        if (n)
-                               spin_unlock(&n->list_lock);
+                               raw_spin_unlock(&n->list_lock);
 
                        n = n2;
-                       spin_lock(&n->list_lock);
+                       raw_spin_lock(&n->list_lock);
                }
 
                do {
@@ -2203,7 +2232,7 @@ static void unfreeze_partials(struct kmem_cache *s,
        }
 
        if (n)
-               spin_unlock(&n->list_lock);
+               raw_spin_unlock(&n->list_lock);
 
        while (discard_page) {
                page = discard_page;
@@ -2242,14 +2271,21 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
                        pobjects = oldpage->pobjects;
                        pages = oldpage->pages;
                        if (drain && pobjects > s->cpu_partial) {
+                               struct slub_free_list *f;
                                unsigned long flags;
+                               LIST_HEAD(tofree);
                                /*
                                 * partial array is full. Move the existing
                                 * set to the per node partial list.
                                 */
                                local_irq_save(flags);
                                unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
+                               f = this_cpu_ptr(&slub_free_list);
+                               raw_spin_lock(&f->lock);
+                               list_splice_init(&f->list, &tofree);
+                               raw_spin_unlock(&f->lock);
                                local_irq_restore(flags);
+                               free_delayed(&tofree);
                                oldpage = NULL;
                                pobjects = 0;
                                pages = 0;
@@ -2319,7 +2355,22 @@ static bool has_cpu_slab(int cpu, void *info)
 
 static void flush_all(struct kmem_cache *s)
 {
+       LIST_HEAD(tofree);
+       int cpu;
+
        on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
+       for_each_online_cpu(cpu) {
+               struct slub_free_list *f;
+
+               if (!has_cpu_slab(cpu, s))
+                       continue;
+
+               f = &per_cpu(slub_free_list, cpu);
+               raw_spin_lock_irq(&f->lock);
+               list_splice_init(&f->list, &tofree);
+               raw_spin_unlock_irq(&f->lock);
+               free_delayed(&tofree);
+       }
 }
 
 /*
@@ -2374,10 +2425,10 @@ static unsigned long count_partial(struct kmem_cache_node *n,
        unsigned long x = 0;
        struct page *page;
 
-       spin_lock_irqsave(&n->list_lock, flags);
+       raw_spin_lock_irqsave(&n->list_lock, flags);
        list_for_each_entry(page, &n->partial, lru)
                x += get_count(page);
-       spin_unlock_irqrestore(&n->list_lock, flags);
+       raw_spin_unlock_irqrestore(&n->list_lock, flags);
        return x;
 }
 #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */
@@ -2515,8 +2566,10 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
  * already disabled (which is the case for bulk allocation).
  */
 static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
-                         unsigned long addr, struct kmem_cache_cpu *c)
+                         unsigned long addr, struct kmem_cache_cpu *c,
+                         struct list_head *to_free)
 {
+       struct slub_free_list *f;
        void *freelist;
        struct page *page;
 
@@ -2572,6 +2625,13 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
        VM_BUG_ON(!c->page->frozen);
        c->freelist = get_freepointer(s, freelist);
        c->tid = next_tid(c->tid);
+
+out:
+       f = this_cpu_ptr(&slub_free_list);
+       raw_spin_lock(&f->lock);
+       list_splice_init(&f->list, to_free);
+       raw_spin_unlock(&f->lock);
+
        return freelist;
 
 new_slab:
@@ -2587,7 +2647,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 
        if (unlikely(!freelist)) {
                slab_out_of_memory(s, gfpflags, node);
-               return NULL;
+               goto out;
        }
 
        page = c->page;
@@ -2600,7 +2660,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
                goto new_slab;  /* Slab failed checks. Next slab needed */
 
        deactivate_slab(s, page, get_freepointer(s, freelist), c);
-       return freelist;
+       goto out;
 }
 
 /*
@@ -2612,6 +2672,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 {
        void *p;
        unsigned long flags;
+       LIST_HEAD(tofree);
 
        local_irq_save(flags);
 #ifdef CONFIG_PREEMPT
@@ -2623,8 +2684,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
        c = this_cpu_ptr(s->cpu_slab);
 #endif
 
-       p = ___slab_alloc(s, gfpflags, node, addr, c);
+       p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree);
        local_irq_restore(flags);
+       free_delayed(&tofree);
        return p;
 }
 
@@ -2810,7 +2872,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 
        do {
                if (unlikely(n)) {
-                       spin_unlock_irqrestore(&n->list_lock, flags);
+                       raw_spin_unlock_irqrestore(&n->list_lock, flags);
                        n = NULL;
                }
                prior = page->freelist;
@@ -2842,7 +2904,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
                                 * Otherwise the list_lock will synchronize with
                                 * other processors updating the list of slabs.
                                 */
-                               spin_lock_irqsave(&n->list_lock, flags);
+                               raw_spin_lock_irqsave(&n->list_lock, flags);
 
                        }
                }
@@ -2884,7 +2946,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
                add_partial(n, page, DEACTIVATE_TO_TAIL);
                stat(s, FREE_ADD_PARTIAL);
        }
-       spin_unlock_irqrestore(&n->list_lock, flags);
+       raw_spin_unlock_irqrestore(&n->list_lock, flags);
        return;
 
 slab_empty:
@@ -2899,7 +2961,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
                remove_full(s, n, page);
        }
 
-       spin_unlock_irqrestore(&n->list_lock, flags);
+       raw_spin_unlock_irqrestore(&n->list_lock, flags);
        stat(s, FREE_SLAB);
        discard_slab(s, page);
 }
@@ -3104,6 +3166,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
                          void **p)
 {
        struct kmem_cache_cpu *c;
+       LIST_HEAD(to_free);
        int i;
 
        /* memcg and kmem_cache debug support */
@@ -3127,7 +3190,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
                         * of re-populating per CPU c->freelist
                         */
                        p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE,
-                                           _RET_IP_, c);
+                                           _RET_IP_, c, &to_free);
                        if (unlikely(!p[i]))
                                goto error;
 
@@ -3139,6 +3202,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
        }
        c->tid = next_tid(c->tid);
        local_irq_enable();
+       free_delayed(&to_free);
 
        /* Clear memory outside IRQ disabled fastpath loop */
        if (unlikely(flags & __GFP_ZERO)) {
@@ -3153,6 +3217,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
        return i;
 error:
        local_irq_enable();
+       free_delayed(&to_free);
        slab_post_alloc_hook(s, flags, i, p);
        __kmem_cache_free_bulk(s, i, p);
        return 0;
@@ -3286,7 +3351,7 @@ static void
 init_kmem_cache_node(struct kmem_cache_node *n)
 {
        n->nr_partial = 0;
-       spin_lock_init(&n->list_lock);
+       raw_spin_lock_init(&n->list_lock);
        INIT_LIST_HEAD(&n->partial);
 #ifdef CONFIG_SLUB_DEBUG
        atomic_long_set(&n->nr_slabs, 0);
@@ -3640,6 +3705,10 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
                                                        const char *text)
 {
 #ifdef CONFIG_SLUB_DEBUG
+#ifdef CONFIG_PREEMPT_RT_BASE
+       /* XXX move out of irq-off section */
+       slab_err(s, page, text, s->name);
+#else
        void *addr = page_address(page);
        void *p;
        unsigned long *map = kzalloc(BITS_TO_LONGS(page->objects) *
@@ -3660,6 +3729,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
        slab_unlock(page);
        kfree(map);
 #endif
+#endif
 }
 
 /*
@@ -3673,7 +3743,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
        struct page *page, *h;
 
        BUG_ON(irqs_disabled());
-       spin_lock_irq(&n->list_lock);
+       raw_spin_lock_irq(&n->list_lock);
        list_for_each_entry_safe(page, h, &n->partial, lru) {
                if (!page->inuse) {
                        remove_partial(n, page);
@@ -3683,7 +3753,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
                        "Objects remaining in %s on __kmem_cache_shutdown()");
                }
        }
-       spin_unlock_irq(&n->list_lock);
+       raw_spin_unlock_irq(&n->list_lock);
 
        list_for_each_entry_safe(page, h, &discard, lru)
                discard_slab(s, page);
@@ -3927,7 +3997,7 @@ int __kmem_cache_shrink(struct kmem_cache *s)
                for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
                        INIT_LIST_HEAD(promote + i);
 
-               spin_lock_irqsave(&n->list_lock, flags);
+               raw_spin_lock_irqsave(&n->list_lock, flags);
 
                /*
                 * Build lists of slabs to discard or promote.
@@ -3958,7 +4028,7 @@ int __kmem_cache_shrink(struct kmem_cache *s)
                for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--)
                        list_splice(promote + i, &n->partial);
 
-               spin_unlock_irqrestore(&n->list_lock, flags);
+               raw_spin_unlock_irqrestore(&n->list_lock, flags);
 
                /* Release empty slabs */
                list_for_each_entry_safe(page, t, &discard, lru)
@@ -4171,6 +4241,12 @@ void __init kmem_cache_init(void)
 {
        static __initdata struct kmem_cache boot_kmem_cache,
                boot_kmem_cache_node;
+       int cpu;
+
+       for_each_possible_cpu(cpu) {
+               raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock);
+               INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list);
+       }
 
        if (debug_guardpage_minorder())
                slub_max_order = 0;
@@ -4379,7 +4455,7 @@ static int validate_slab_node(struct kmem_cache *s,
        struct page *page;
        unsigned long flags;
 
-       spin_lock_irqsave(&n->list_lock, flags);
+       raw_spin_lock_irqsave(&n->list_lock, flags);
 
        list_for_each_entry(page, &n->partial, lru) {
                validate_slab_slab(s, page, map);
@@ -4401,7 +4477,7 @@ static int validate_slab_node(struct kmem_cache *s,
                       s->name, count, atomic_long_read(&n->nr_slabs));
 
 out:
-       spin_unlock_irqrestore(&n->list_lock, flags);
+       raw_spin_unlock_irqrestore(&n->list_lock, flags);
        return count;
 }
 
@@ -4589,12 +4665,12 @@ static int list_locations(struct kmem_cache *s, char *buf,
                if (!atomic_long_read(&n->nr_slabs))
                        continue;
 
-               spin_lock_irqsave(&n->list_lock, flags);
+               raw_spin_lock_irqsave(&n->list_lock, flags);
                list_for_each_entry(page, &n->partial, lru)
                        process_slab(&t, s, page, alloc, map);
                list_for_each_entry(page, &n->full, lru)
                        process_slab(&t, s, page, alloc, map);
-               spin_unlock_irqrestore(&n->list_lock, flags);
+               raw_spin_unlock_irqrestore(&n->list_lock, flags);
        }
 
        for (i = 0; i < t.count; i++) {
diff --git a/mm/swap.c b/mm/swap.c
index a77d68f2c1b6..30d62efe001b 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -32,6 +32,7 @@
 #include <linux/memcontrol.h>
 #include <linux/gfp.h>
 #include <linux/uio.h>
+#include <linux/locallock.h>
 #include <linux/hugetlb.h>
 #include <linux/page_idle.h>
 
@@ -50,6 +51,8 @@ static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs);
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
 #endif
+static DEFINE_LOCAL_IRQ_LOCK(rotate_lock);
+DEFINE_LOCAL_IRQ_LOCK(swapvec_lock);
 
 /*
  * This path almost never happens for VM activity - pages are normally
@@ -252,11 +255,11 @@ void rotate_reclaimable_page(struct page *page)
                unsigned long flags;
 
                get_page(page);
-               local_irq_save(flags);
+               local_lock_irqsave(rotate_lock, flags);
                pvec = this_cpu_ptr(&lru_rotate_pvecs);
                if (!pagevec_add(pvec, page) || PageCompound(page))
                        pagevec_move_tail(pvec);
-               local_irq_restore(flags);
+               local_unlock_irqrestore(rotate_lock, flags);
        }
 }
 
@@ -306,12 +309,13 @@ void activate_page(struct page *page)
 {
        page = compound_head(page);
        if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-               struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+               struct pagevec *pvec = &get_locked_var(swapvec_lock,
+                                                      activate_page_pvecs);
 
                get_page(page);
                if (!pagevec_add(pvec, page) || PageCompound(page))
                        pagevec_lru_move_fn(pvec, __activate_page, NULL);
-               put_cpu_var(activate_page_pvecs);
+               put_locked_var(swapvec_lock, activate_page_pvecs);
        }
 }
 
@@ -338,7 +342,7 @@ void activate_page(struct page *page)
 
 static void __lru_cache_activate_page(struct page *page)
 {
-       struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+       struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec);
        int i;
 
        /*
@@ -360,7 +364,7 @@ static void __lru_cache_activate_page(struct page *page)
                }
        }
 
-       put_cpu_var(lru_add_pvec);
+       put_locked_var(swapvec_lock, lru_add_pvec);
 }
 
 /*
@@ -402,12 +406,12 @@ EXPORT_SYMBOL(mark_page_accessed);
 
 static void __lru_cache_add(struct page *page)
 {
-       struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+       struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec);
 
        get_page(page);
        if (!pagevec_add(pvec, page) || PageCompound(page))
                __pagevec_lru_add(pvec);
-       put_cpu_var(lru_add_pvec);
+       put_locked_var(swapvec_lock, lru_add_pvec);
 }
 
 /**
@@ -613,9 +617,15 @@ void lru_add_drain_cpu(int cpu)
                unsigned long flags;
 
                /* No harm done if a racing interrupt already did this */
-               local_irq_save(flags);
+#ifdef CONFIG_PREEMPT_RT_BASE
+               local_lock_irqsave_on(rotate_lock, flags, cpu);
                pagevec_move_tail(pvec);
-               local_irq_restore(flags);
+               local_unlock_irqrestore_on(rotate_lock, flags, cpu);
+#else
+               local_lock_irqsave(rotate_lock, flags);
+               pagevec_move_tail(pvec);
+               local_unlock_irqrestore(rotate_lock, flags);
+#endif
        }
 
        pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
@@ -647,11 +657,12 @@ void deactivate_file_page(struct page *page)
                return;
 
        if (likely(get_page_unless_zero(page))) {
-               struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
+               struct pagevec *pvec = &get_locked_var(swapvec_lock,
+                                                      lru_deactivate_file_pvecs);
 
                if (!pagevec_add(pvec, page) || PageCompound(page))
                        pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
-               put_cpu_var(lru_deactivate_file_pvecs);
+               put_locked_var(swapvec_lock, lru_deactivate_file_pvecs);
        }
 }
 
@@ -666,21 +677,32 @@ void mark_page_lazyfree(struct page *page)
 {
        if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
            !PageSwapCache(page) && !PageUnevictable(page)) {
-               struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
+               struct pagevec *pvec = &get_locked_var(swapvec_lock,
+                                                      lru_lazyfree_pvecs);
 
                get_page(page);
                if (!pagevec_add(pvec, page) || PageCompound(page))
                        pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
-               put_cpu_var(lru_lazyfree_pvecs);
+               put_locked_var(swapvec_lock, lru_lazyfree_pvecs);
        }
 }
 
 void lru_add_drain(void)
 {
-       lru_add_drain_cpu(get_cpu());
-       put_cpu();
+       lru_add_drain_cpu(local_lock_cpu(swapvec_lock));
+       local_unlock_cpu(swapvec_lock);
+}
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work)
+{
+       local_lock_on(swapvec_lock, cpu);
+       lru_add_drain_cpu(cpu);
+       local_unlock_on(swapvec_lock, cpu);
 }
 
+#else
+
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
        lru_add_drain();
@@ -688,6 +710,16 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
+static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work)
+{
+       struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
+
+       INIT_WORK(work, lru_add_drain_per_cpu);
+       queue_work_on(cpu, mm_percpu_wq, work);
+       cpumask_set_cpu(cpu, has_work);
+}
+#endif
+
 void lru_add_drain_all_cpuslocked(void)
 {
        static DEFINE_MUTEX(lock);
@@ -705,21 +737,19 @@ void lru_add_drain_all_cpuslocked(void)
        cpumask_clear(&has_work);
 
        for_each_online_cpu(cpu) {
-               struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
                if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
                    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
                    pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
                    pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) ||
-                   need_activate_page_drain(cpu)) {
-                       INIT_WORK(work, lru_add_drain_per_cpu);
-                       queue_work_on(cpu, mm_percpu_wq, work);
-                       cpumask_set_cpu(cpu, &has_work);
-               }
+                   need_activate_page_drain(cpu))
+                       remote_lru_add_drain(cpu, &has_work);
        }
 
+#ifndef CONFIG_PREEMPT_RT_BASE
        for_each_cpu(cpu, &has_work)
                flush_work(&per_cpu(lru_add_drain_work, cpu));
+#endif
 
        mutex_unlock(&lock);
 }
diff --git a/mm/truncate.c b/mm/truncate.c
index 2330223841fb..d0c8e6c8fef5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -41,8 +41,10 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
                goto unlock;
        if (*slot != entry)
                goto unlock;
+       local_lock(shadow_nodes_lock);
        __radix_tree_replace(&mapping->page_tree, node, slot, NULL,
-                            workingset_update_node, mapping);
+                            __workingset_update_node, mapping);
+       local_unlock(shadow_nodes_lock);
        mapping->nrexceptional--;
 unlock:
        spin_unlock_irq(&mapping->tree_lock);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 9ff21a12ea00..95c83b291548 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -865,7 +865,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
        struct vmap_block *vb;
        struct vmap_area *va;
        unsigned long vb_idx;
-       int node, err;
+       int node, err, cpu;
        void *vaddr;
 
        node = numa_node_id();
@@ -908,11 +908,12 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
        BUG_ON(err);
        radix_tree_preload_end();
 
-       vbq = &get_cpu_var(vmap_block_queue);
+       cpu = get_cpu_light();
+       vbq = this_cpu_ptr(&vmap_block_queue);
        spin_lock(&vbq->lock);
        list_add_tail_rcu(&vb->free_list, &vbq->free);
        spin_unlock(&vbq->lock);
-       put_cpu_var(vmap_block_queue);
+       put_cpu_light();
 
        return vaddr;
 }
@@ -981,6 +982,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
        struct vmap_block *vb;
        void *vaddr = NULL;
        unsigned int order;
+       int cpu;
 
        BUG_ON(offset_in_page(size));
        BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
@@ -995,7 +997,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
        order = get_order(size);
 
        rcu_read_lock();
-       vbq = &get_cpu_var(vmap_block_queue);
+       cpu = get_cpu_light();
+       vbq = this_cpu_ptr(&vmap_block_queue);
        list_for_each_entry_rcu(vb, &vbq->free, free_list) {
                unsigned long pages_off;
 
@@ -1018,7 +1021,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
                break;
        }
 
-       put_cpu_var(vmap_block_queue);
+       put_cpu_light();
        rcu_read_unlock();
 
        /* Allocate new block if nothing was found */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 527ae727d547..ae6446b054d3 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -249,6 +249,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
        long x;
        long t;
 
+       preempt_disable_rt();
        x = delta + __this_cpu_read(*p);
 
        t = __this_cpu_read(pcp->stat_threshold);
@@ -258,6 +259,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
                x = 0;
        }
        __this_cpu_write(*p, x);
+       preempt_enable_rt();
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
@@ -269,6 +271,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
        long x;
        long t;
 
+       preempt_disable_rt();
        x = delta + __this_cpu_read(*p);
 
        t = __this_cpu_read(pcp->stat_threshold);
@@ -278,6 +281,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
                x = 0;
        }
        __this_cpu_write(*p, x);
+       preempt_enable_rt();
 }
 EXPORT_SYMBOL(__mod_node_page_state);
 
@@ -310,6 +314,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
        s8 __percpu *p = pcp->vm_stat_diff + item;
        s8 v, t;
 
+       preempt_disable_rt();
        v = __this_cpu_inc_return(*p);
        t = __this_cpu_read(pcp->stat_threshold);
        if (unlikely(v > t)) {
@@ -318,6 +323,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
                zone_page_state_add(v + overstep, zone, item);
                __this_cpu_write(*p, -overstep);
        }
+       preempt_enable_rt();
 }
 
 void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -326,6 +332,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
        s8 __percpu *p = pcp->vm_node_stat_diff + item;
        s8 v, t;
 
+       preempt_disable_rt();
        v = __this_cpu_inc_return(*p);
        t = __this_cpu_read(pcp->stat_threshold);
        if (unlikely(v > t)) {
@@ -334,6 +341,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
                node_page_state_add(v + overstep, pgdat, item);
                __this_cpu_write(*p, -overstep);
        }
+       preempt_enable_rt();
 }
 
 void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
@@ -354,6 +362,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
        s8 __percpu *p = pcp->vm_stat_diff + item;
        s8 v, t;
 
+       preempt_disable_rt();
        v = __this_cpu_dec_return(*p);
        t = __this_cpu_read(pcp->stat_threshold);
        if (unlikely(v < - t)) {
@@ -362,6 +371,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
                zone_page_state_add(v - overstep, zone, item);
                __this_cpu_write(*p, overstep);
        }
+       preempt_enable_rt();
 }
 
 void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -370,6 +380,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
        s8 __percpu *p = pcp->vm_node_stat_diff + item;
        s8 v, t;
 
+       preempt_disable_rt();
        v = __this_cpu_dec_return(*p);
        t = __this_cpu_read(pcp->stat_threshold);
        if (unlikely(v < - t)) {
@@ -378,6 +389,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
                node_page_state_add(v - overstep, pgdat, item);
                __this_cpu_write(*p, overstep);
        }
+       preempt_enable_rt();
 }
 
 void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
diff --git a/mm/workingset.c b/mm/workingset.c
index b997c9de28f6..e252cc69a3d4 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -338,9 +338,10 @@ void workingset_activation(struct page *page)
  * point where they would still be useful.
  */
 
-static struct list_lru shadow_nodes;
+static struct list_lru __shadow_nodes;
+DEFINE_LOCAL_IRQ_LOCK(shadow_nodes_lock);
 
-void workingset_update_node(struct radix_tree_node *node, void *private)
+void __workingset_update_node(struct radix_tree_node *node, void *private)
 {
        struct address_space *mapping = private;
 
@@ -358,10 +359,10 @@ void workingset_update_node(struct radix_tree_node *node, void *private)
         */
        if (node->count && node->count == node->exceptional) {
                if (list_empty(&node->private_list))
-                       list_lru_add(&shadow_nodes, &node->private_list);
+                       list_lru_add(&__shadow_nodes, &node->private_list);
        } else {
                if (!list_empty(&node->private_list))
-                       list_lru_del(&shadow_nodes, &node->private_list);
+                       list_lru_del(&__shadow_nodes, &node->private_list);
        }
 }
 
@@ -373,9 +374,9 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
        unsigned long cache;
 
        /* list_lru lock nests inside IRQ-safe mapping->tree_lock */
-       local_irq_disable();
-       nodes = list_lru_shrink_count(&shadow_nodes, sc);
-       local_irq_enable();
+       local_lock_irq(shadow_nodes_lock);
+       nodes = list_lru_shrink_count(&__shadow_nodes, sc);
+       local_unlock_irq(shadow_nodes_lock);
 
        /*
         * Approximate a reasonable limit for the radix tree nodes
@@ -475,15 +476,15 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
                goto out_invalid;
        inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
        __radix_tree_delete_node(&mapping->page_tree, node,
-                                workingset_update_node, mapping);
+                                __workingset_update_node, mapping);
 
 out_invalid:
        spin_unlock(&mapping->tree_lock);
        ret = LRU_REMOVED_RETRY;
 out:
-       local_irq_enable();
+       local_unlock_irq(shadow_nodes_lock);
        cond_resched();
-       local_irq_disable();
+       local_lock_irq(shadow_nodes_lock);
        spin_lock(lru_lock);
        return ret;
 }
@@ -494,9 +495,9 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
        unsigned long ret;
 
        /* list_lru lock nests inside IRQ-safe mapping->tree_lock */
-       local_irq_disable();
-       ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL);
-       local_irq_enable();
+       local_lock_irq(shadow_nodes_lock);
+       ret = list_lru_shrink_walk(&__shadow_nodes, sc, shadow_lru_isolate, NULL);
+       local_unlock_irq(shadow_nodes_lock);
        return ret;
 }
 
@@ -534,7 +535,7 @@ static int __init workingset_init(void)
        pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
               timestamp_bits, max_order, bucket_order);
 
-       ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key);
+       ret = __list_lru_init(&__shadow_nodes, true, &shadow_nodes_key);
        if (ret)
                goto err;
        ret = register_shrinker(&workingset_shadow_shrinker);
@@ -542,7 +543,7 @@ static int __init workingset_init(void)
                goto err_list_lru;
        return 0;
 err_list_lru:
-       list_lru_destroy(&shadow_nodes);
+       list_lru_destroy(&__shadow_nodes);
 err:
        return ret;
 }
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 685049a9048d..8d1489fd1dbc 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -53,6 +53,7 @@
 #include <linux/mount.h>
 #include <linux/migrate.h>
 #include <linux/pagemap.h>
+#include <linux/locallock.h>
 
 #define ZSPAGE_MAGIC   0x58
 
@@ -70,9 +71,22 @@
  */
 #define ZS_MAX_ZSPAGE_ORDER 2
 #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
-
 #define ZS_HANDLE_SIZE (sizeof(unsigned long))
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+struct zsmalloc_handle {
+       unsigned long addr;
+       struct mutex lock;
+};
+
+#define ZS_HANDLE_ALLOC_SIZE (sizeof(struct zsmalloc_handle))
+
+#else
+
+#define ZS_HANDLE_ALLOC_SIZE (sizeof(unsigned long))
+#endif
+
 /*
  * Object location (<PFN>, <obj_idx>) is encoded as
  * as single (unsigned long) handle value.
@@ -320,7 +334,7 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {}
 
 static int create_cache(struct zs_pool *pool)
 {
-       pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
+       pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_ALLOC_SIZE,
                                        0, 0, NULL);
        if (!pool->handle_cachep)
                return 1;
@@ -344,10 +358,27 @@ static void destroy_cache(struct zs_pool *pool)
 
 static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp)
 {
-       return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
-                       gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
+       void *p;
+
+       p = kmem_cache_alloc(pool->handle_cachep,
+                            gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
+#ifdef CONFIG_PREEMPT_RT_FULL
+       if (p) {
+               struct zsmalloc_handle *zh = p;
+
+               mutex_init(&zh->lock);
+       }
+#endif
+       return (unsigned long)p;
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static struct zsmalloc_handle *zs_get_pure_handle(unsigned long handle)
+{
+       return (void *)(handle &~((1 << OBJ_TAG_BITS) - 1));
+}
+#endif
+
 static void cache_free_handle(struct zs_pool *pool, unsigned long handle)
 {
        kmem_cache_free(pool->handle_cachep, (void *)handle);
@@ -366,12 +397,18 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
 
 static void record_obj(unsigned long handle, unsigned long obj)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+       WRITE_ONCE(zh->addr, obj);
+#else
        /*
         * lsb of @obj represents handle lock while other bits
         * represent object value the handle is pointing so
         * updating shouldn't do store tearing.
         */
        WRITE_ONCE(*(unsigned long *)handle, obj);
+#endif
 }
 
 /* zpool driver */
@@ -460,6 +497,7 @@ MODULE_ALIAS("zpool-zsmalloc");
 
 /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
 static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
+static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock);
 
 static bool is_zspage_isolated(struct zspage *zspage)
 {
@@ -898,7 +936,13 @@ static unsigned long location_to_obj(struct page *page, unsigned int obj_idx)
 
 static unsigned long handle_to_obj(unsigned long handle)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+       return zh->addr;
+#else
        return *(unsigned long *)handle;
+#endif
 }
 
 static unsigned long obj_to_head(struct page *page, void *obj)
@@ -912,22 +956,46 @@ static unsigned long obj_to_head(struct page *page, void *obj)
 
 static inline int testpin_tag(unsigned long handle)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+       return mutex_is_locked(&zh->lock);
+#else
        return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
 }
 
 static inline int trypin_tag(unsigned long handle)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+       return mutex_trylock(&zh->lock);
+#else
        return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
 }
 
 static void pin_tag(unsigned long handle)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+       return mutex_lock(&zh->lock);
+#else
        bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
 }
 
 static void unpin_tag(unsigned long handle)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+       struct zsmalloc_handle *zh = zs_get_pure_handle(handle);
+
+       return mutex_unlock(&zh->lock);
+#else
        bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle);
+#endif
 }
 
 static void reset_page(struct page *page)
@@ -1365,7 +1433,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
        class = pool->size_class[class_idx];
        off = (class->size * obj_idx) & ~PAGE_MASK;
 
-       area = &get_cpu_var(zs_map_area);
+       area = &get_locked_var(zs_map_area_lock, zs_map_area);
        area->vm_mm = mm;
        if (off + class->size <= PAGE_SIZE) {
                /* this object is contained entirely within a page */
@@ -1419,7 +1487,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 
                __zs_unmap_object(area, pages, off, class->size);
        }
-       put_cpu_var(zs_map_area);
+       put_locked_var(zs_map_area_lock, zs_map_area);
 
        migrate_read_unlock(zspage);
        unpin_tag(handle);
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index c10bdf63eae7..84a49f2bcfbc 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -38,7 +38,6 @@
 
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
diff --git a/net/Kconfig b/net/Kconfig
index 9dba2715919d..9c7b38379c09 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -272,7 +272,7 @@ config CGROUP_NET_CLASSID
 
 config NET_RX_BUSY_POLL
        bool
-       default y
+       default y if !PREEMPT_RT_FULL
 
 config BQL
        bool
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 65d734c165bd..923e9a271872 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -251,15 +251,13 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 }
 
 /* Send frame to sockets with specific channel */
-void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
-                        int flag, struct sock *skip_sk)
+static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+                                 int flag, struct sock *skip_sk)
 {
        struct sock *sk;
 
        BT_DBG("channel %u len %d", channel, skb->len);
 
-       read_lock(&hci_sk_list.lock);
-
        sk_for_each(sk, &hci_sk_list.head) {
                struct sk_buff *nskb;
 
@@ -285,6 +283,13 @@ void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
                        kfree_skb(nskb);
        }
 
+}
+
+void hci_send_to_channel(unsigned short channel, struct sk_buff *skb,
+                        int flag, struct sock *skip_sk)
+{
+       read_lock(&hci_sk_list.lock);
+       __hci_send_to_channel(channel, skb, flag, skip_sk);
        read_unlock(&hci_sk_list.lock);
 }
 
@@ -388,8 +393,8 @@ void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event,
                hdr->index = index;
                hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE);
 
-               hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
-                                   HCI_SOCK_TRUSTED, NULL);
+               __hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
+                                     HCI_SOCK_TRUSTED, NULL);
                kfree_skb(skb);
        }
 
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 13690334efa3..9cc67ac257f1 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -102,7 +102,6 @@ struct bcm_op {
        unsigned long frames_abs, frames_filtered;
        struct bcm_timeval ival1, ival2;
        struct hrtimer timer, thrtimer;
-       struct tasklet_struct tsklet, thrtsklet;
        ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
        int rx_ifindex;
        int cfsiz;
@@ -364,25 +363,34 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
        }
 }
 
-static void bcm_tx_start_timer(struct bcm_op *op)
+static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt)
 {
+       ktime_t ival;
+
        if (op->kt_ival1 && op->count)
-               hrtimer_start(&op->timer,
-                             ktime_add(ktime_get(), op->kt_ival1),
-                             HRTIMER_MODE_ABS);
+               ival = op->kt_ival1;
        else if (op->kt_ival2)
-               hrtimer_start(&op->timer,
-                             ktime_add(ktime_get(), op->kt_ival2),
-                             HRTIMER_MODE_ABS);
+               ival = op->kt_ival2;
+       else
+               return false;
+
+       hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival));
+       return true;
 }
 
-static void bcm_tx_timeout_tsklet(unsigned long data)
+static void bcm_tx_start_timer(struct bcm_op *op)
 {
-       struct bcm_op *op = (struct bcm_op *)data;
+       if (bcm_tx_set_expiry(op, &op->timer))
+               hrtimer_start_expires(&op->timer, HRTIMER_MODE_ABS_SOFT);
+}
+
+/* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */
+static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
+{
+       struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
        struct bcm_msg_head msg_head;
 
        if (op->kt_ival1 && (op->count > 0)) {
-
                op->count--;
                if (!op->count && (op->flags & TX_COUNTEVT)) {
 
@@ -399,22 +407,12 @@ static void bcm_tx_timeout_tsklet(unsigned long data)
                }
                bcm_can_tx(op);
 
-       } else if (op->kt_ival2)
+       } else if (op->kt_ival2) {
                bcm_can_tx(op);
+       }
 
-       bcm_tx_start_timer(op);
-}
-
-/*
- * bcm_tx_timeout_handler - performs cyclic CAN frame transmissions
- */
-static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer)
-{
-       struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
-
-       tasklet_schedule(&op->tsklet);
-
-       return HRTIMER_NORESTART;
+       return bcm_tx_set_expiry(op, &op->timer) ?
+               HRTIMER_RESTART : HRTIMER_NORESTART;
 }
 
 /*
@@ -480,7 +478,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op,
                /* do not send the saved data - only start throttle timer */
                hrtimer_start(&op->thrtimer,
                              ktime_add(op->kt_lastmsg, op->kt_ival2),
-                             HRTIMER_MODE_ABS);
+                             HRTIMER_MODE_ABS_SOFT);
                return;
        }
 
@@ -539,14 +537,21 @@ static void bcm_rx_starttimer(struct bcm_op *op)
                return;
 
        if (op->kt_ival1)
-               hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL);
+               hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT);
 }
 
-static void bcm_rx_timeout_tsklet(unsigned long data)
+/* bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out */
+static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 {
-       struct bcm_op *op = (struct bcm_op *)data;
+       struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
        struct bcm_msg_head msg_head;
 
+       /* if user wants to be informed, when cyclic CAN-Messages come back */
+       if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
+               /* clear received CAN frames to indicate 'nothing received' */
+               memset(op->last_frames, 0, op->nframes * op->cfsiz);
+       }
+
        /* create notification to user */
        msg_head.opcode  = RX_TIMEOUT;
        msg_head.flags   = op->flags;
@@ -557,25 +562,6 @@ static void bcm_rx_timeout_tsklet(unsigned long data)
        msg_head.nframes = 0;
 
        bcm_send_to_user(op, &msg_head, NULL, 0);
-}
-
-/*
- * bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out
- */
-static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
-{
-       struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer);
-
-       /* schedule before NET_RX_SOFTIRQ */
-       tasklet_hi_schedule(&op->tsklet);
-
-       /* no restart of the timer is done here! */
-
-       /* if user wants to be informed, when cyclic CAN-Messages come back */
-       if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
-               /* clear received CAN frames to indicate 'nothing received' */
-               memset(op->last_frames, 0, op->nframes * op->cfsiz);
-       }
 
        return HRTIMER_NORESTART;
 }
@@ -583,14 +569,12 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer)
 /*
  * bcm_rx_do_flush - helper for bcm_rx_thr_flush
  */
-static inline int bcm_rx_do_flush(struct bcm_op *op, int update,
-                                 unsigned int index)
+static inline int bcm_rx_do_flush(struct bcm_op *op, unsigned int index)
 {
        struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
 
        if ((op->last_frames) && (lcf->flags & RX_THR)) {
-               if (update)
-                       bcm_rx_changed(op, lcf);
+               bcm_rx_changed(op, lcf);
                return 1;
        }
        return 0;
@@ -598,11 +582,8 @@ static inline int bcm_rx_do_flush(struct bcm_op *op, int update,
 
 /*
  * bcm_rx_thr_flush - Check for throttled data and send it to the userspace
- *
- * update == 0 : just check if throttled data is available  (any irq context)
- * update == 1 : check and send throttled data to userspace (soft_irq context)
  */
-static int bcm_rx_thr_flush(struct bcm_op *op, int update)
+static int bcm_rx_thr_flush(struct bcm_op *op)
 {
        int updated = 0;
 
@@ -611,24 +592,16 @@ static int bcm_rx_thr_flush(struct bcm_op *op, int update)
 
                /* for MUX filter we start at index 1 */
                for (i = 1; i < op->nframes; i++)
-                       updated += bcm_rx_do_flush(op, update, i);
+                       updated += bcm_rx_do_flush(op, i);
 
        } else {
                /* for RX_FILTER_ID and simple filter */
-               updated += bcm_rx_do_flush(op, update, 0);
+               updated += bcm_rx_do_flush(op, 0);
        }
 
        return updated;
 }
 
-static void bcm_rx_thr_tsklet(unsigned long data)
-{
-       struct bcm_op *op = (struct bcm_op *)data;
-
-       /* push the changed data to the userspace */
-       bcm_rx_thr_flush(op, 1);
-}
-
 /*
  * bcm_rx_thr_handler - the time for blocked content updates is over now:
  *                      Check for throttled data and send it to the userspace
@@ -637,9 +610,7 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
 {
        struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer);
 
-       tasklet_schedule(&op->thrtsklet);
-
-       if (bcm_rx_thr_flush(op, 0)) {
+       if (bcm_rx_thr_flush(op)) {
                hrtimer_forward(hrtimer, ktime_get(), op->kt_ival2);
                return HRTIMER_RESTART;
        } else {
@@ -735,23 +706,8 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
 
 static void bcm_remove_op(struct bcm_op *op)
 {
-       if (op->tsklet.func) {
-               while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) ||
-                      test_bit(TASKLET_STATE_RUN, &op->tsklet.state) ||
-                      hrtimer_active(&op->timer)) {
-                       hrtimer_cancel(&op->timer);
-                       tasklet_kill(&op->tsklet);
-               }
-       }
-
-       if (op->thrtsklet.func) {
-               while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) ||
-                      test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) ||
-                      hrtimer_active(&op->thrtimer)) {
-                       hrtimer_cancel(&op->thrtimer);
-                       tasklet_kill(&op->thrtsklet);
-               }
-       }
+       hrtimer_cancel(&op->timer);
+       hrtimer_cancel(&op->thrtimer);
 
        if ((op->frames) && (op->frames != &op->sframe))
                kfree(op->frames);
@@ -979,15 +935,13 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
                op->ifindex = ifindex;
 
                /* initialize uninitialized (kzalloc) structure */
-               hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+               hrtimer_init(&op->timer, CLOCK_MONOTONIC,
+                            HRTIMER_MODE_REL_SOFT);
                op->timer.function = bcm_tx_timeout_handler;
 
-               /* initialize tasklet for tx countevent notification */
-               tasklet_init(&op->tsklet, bcm_tx_timeout_tsklet,
-                            (unsigned long) op);
-
                /* currently unused in tx_ops */
-               hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+               hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC,
+                            HRTIMER_MODE_REL_SOFT);
 
                /* add this bcm_op to the list of the tx_ops */
                list_add(&op->list, &bo->tx_ops);
@@ -1150,20 +1104,14 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
                op->rx_ifindex = ifindex;
 
                /* initialize uninitialized (kzalloc) structure */
-               hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+               hrtimer_init(&op->timer, CLOCK_MONOTONIC,
+                            HRTIMER_MODE_REL_SOFT);
                op->timer.function = bcm_rx_timeout_handler;
 
-               /* initialize tasklet for rx timeout notification */
-               tasklet_init(&op->tsklet, bcm_rx_timeout_tsklet,
-                            (unsigned long) op);
-
-               hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+               hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC,
+                            HRTIMER_MODE_REL_SOFT);
                op->thrtimer.function = bcm_rx_thr_handler;
 
-               /* initialize tasklet for rx throttle handling */
-               tasklet_init(&op->thrtsklet, bcm_rx_thr_tsklet,
-                            (unsigned long) op);
-
                /* add this bcm_op to the list of the rx_ops */
                list_add(&op->list, &bo->rx_ops);
 
@@ -1209,12 +1157,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
                         */
                        op->kt_lastmsg = 0;
                        hrtimer_cancel(&op->thrtimer);
-                       bcm_rx_thr_flush(op, 1);
+                       bcm_rx_thr_flush(op);
                }
 
                if ((op->flags & STARTTIMER) && op->kt_ival1)
                        hrtimer_start(&op->timer, op->kt_ival1,
-                                     HRTIMER_MODE_REL);
+                                     HRTIMER_MODE_REL_SOFT);
        }
 
        /* now we can register for can_ids, if we added a new bcm_op */
diff --git a/net/core/dev.c b/net/core/dev.c
index e8a66ad6d07c..fa9642bb0482 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -195,6 +195,7 @@ static unsigned int napi_gen_id = NR_CPUS;
 static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
 
 static seqcount_t devnet_rename_seq;
+static DEFINE_MUTEX(devnet_rename_mutex);
 
 static inline void dev_base_seq_inc(struct net *net)
 {
@@ -217,14 +218,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
 static inline void rps_lock(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-       spin_lock(&sd->input_pkt_queue.lock);
+       raw_spin_lock(&sd->input_pkt_queue.raw_lock);
 #endif
 }
 
 static inline void rps_unlock(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-       spin_unlock(&sd->input_pkt_queue.lock);
+       raw_spin_unlock(&sd->input_pkt_queue.raw_lock);
 #endif
 }
 
@@ -920,7 +921,8 @@ int netdev_get_name(struct net *net, char *name, int ifindex)
        strcpy(name, dev->name);
        rcu_read_unlock();
        if (read_seqcount_retry(&devnet_rename_seq, seq)) {
-               cond_resched();
+               mutex_lock(&devnet_rename_mutex);
+               mutex_unlock(&devnet_rename_mutex);
                goto retry;
        }
 
@@ -1189,20 +1191,17 @@ int dev_change_name(struct net_device *dev, const char *newname)
        if (dev->flags & IFF_UP)
                return -EBUSY;
 
-       write_seqcount_begin(&devnet_rename_seq);
+       mutex_lock(&devnet_rename_mutex);
+       __raw_write_seqcount_begin(&devnet_rename_seq);
 
-       if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
-               write_seqcount_end(&devnet_rename_seq);
-               return 0;
-       }
+       if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
+               goto outunlock;
 
        memcpy(oldname, dev->name, IFNAMSIZ);
 
        err = dev_get_valid_name(net, dev, newname);
-       if (err < 0) {
-               write_seqcount_end(&devnet_rename_seq);
-               return err;
-       }
+       if (err < 0)
+               goto outunlock;
 
        if (oldname[0] && !strchr(oldname, '%'))
                netdev_info(dev, "renamed from %s\n", oldname);
@@ -1215,11 +1214,12 @@ int dev_change_name(struct net_device *dev, const char *newname)
        if (ret) {
                memcpy(dev->name, oldname, IFNAMSIZ);
                dev->name_assign_type = old_assign_type;
-               write_seqcount_end(&devnet_rename_seq);
-               return ret;
+               err = ret;
+               goto outunlock;
        }
 
-       write_seqcount_end(&devnet_rename_seq);
+       __raw_write_seqcount_end(&devnet_rename_seq);
+       mutex_unlock(&devnet_rename_mutex);
 
        netdev_adjacent_rename_links(dev, oldname);
 
@@ -1240,7 +1240,8 @@ int dev_change_name(struct net_device *dev, const char *newname)
                /* err >= 0 after dev_alloc_name() or stores the first errno */
                if (err >= 0) {
                        err = ret;
-                       write_seqcount_begin(&devnet_rename_seq);
+                       mutex_lock(&devnet_rename_mutex);
+                       __raw_write_seqcount_begin(&devnet_rename_seq);
                        memcpy(dev->name, oldname, IFNAMSIZ);
                        memcpy(oldname, newname, IFNAMSIZ);
                        dev->name_assign_type = old_assign_type;
@@ -1253,6 +1254,11 @@ int dev_change_name(struct net_device *dev, const char *newname)
        }
 
        return err;
+
+outunlock:
+       __raw_write_seqcount_end(&devnet_rename_seq);
+       mutex_unlock(&devnet_rename_mutex);
+       return err;
 }
 
 /**
@@ -2460,6 +2466,7 @@ static void __netif_reschedule(struct Qdisc *q)
        sd->output_queue_tailp = &q->next_sched;
        raise_softirq_irqoff(NET_TX_SOFTIRQ);
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 
 void __netif_schedule(struct Qdisc *q)
@@ -2522,6 +2529,7 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
        __this_cpu_write(softnet_data.completion_queue, skb);
        raise_softirq_irqoff(NET_TX_SOFTIRQ);
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(__dev_kfree_skb_irq);
 
@@ -3197,7 +3205,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
         * This permits qdisc->running owner to get the lock more
         * often and dequeue packets faster.
         */
+#ifdef CONFIG_PREEMPT_RT_FULL
+       contended = true;
+#else
        contended = qdisc_is_running(q);
+#endif
        if (unlikely(contended))
                spin_lock(&q->busylock);
 
@@ -3268,8 +3280,10 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 DEFINE_PER_CPU(int, xmit_recursion);
 EXPORT_SYMBOL(xmit_recursion);
+#endif
 
 /**
  *     dev_loopback_xmit - loop back @skb
@@ -3509,9 +3523,12 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
        if (dev->flags & IFF_UP) {
                int cpu = smp_processor_id(); /* ok because BHs are off */
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+               if (txq->xmit_lock_owner != current) {
+#else
                if (txq->xmit_lock_owner != cpu) {
-                       if (unlikely(__this_cpu_read(xmit_recursion) >
-                                    XMIT_RECURSION_LIMIT))
+#endif
+                       if (unlikely(xmit_rec_read() > XMIT_RECURSION_LIMIT))
                                goto recursion_alert;
 
                        skb = validate_xmit_skb(skb, dev);
@@ -3521,9 +3538,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
                        HARD_TX_LOCK(dev, txq, cpu);
 
                        if (!netif_xmit_stopped(txq)) {
-                               __this_cpu_inc(xmit_recursion);
+                               xmit_rec_inc();
                                skb = dev_hard_start_xmit(skb, dev, txq, &rc);
-                               __this_cpu_dec(xmit_recursion);
+                               xmit_rec_dec();
                                if (dev_xmit_complete(rc)) {
                                        HARD_TX_UNLOCK(dev, txq);
                                        goto out;
@@ -3904,6 +3921,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
        rps_unlock(sd);
 
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 
        atomic_long_inc(&skb->dev->rx_dropped);
        kfree_skb(skb);
@@ -4056,7 +4074,7 @@ static int netif_rx_internal(struct sk_buff *skb)
                struct rps_dev_flow voidflow, *rflow = &voidflow;
                int cpu;
 
-               preempt_disable();
+               migrate_disable();
                rcu_read_lock();
 
                cpu = get_rps_cpu(skb->dev, skb, &rflow);
@@ -4066,14 +4084,14 @@ static int netif_rx_internal(struct sk_buff *skb)
                ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 
                rcu_read_unlock();
-               preempt_enable();
+               migrate_enable();
        } else
 #endif
        {
                unsigned int qtail;
 
-               ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
-               put_cpu();
+               ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail);
+               put_cpu_light();
        }
        return ret;
 }
@@ -4107,11 +4125,9 @@ int netif_rx_ni(struct sk_buff *skb)
 
        trace_netif_rx_ni_entry(skb);
 
-       preempt_disable();
+       local_bh_disable();
        err = netif_rx_internal(skb);
-       if (local_softirq_pending())
-               do_softirq();
-       preempt_enable();
+       local_bh_enable();
 
        return err;
 }
@@ -4629,7 +4645,7 @@ static void flush_backlog(struct work_struct *work)
        skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
                if (skb->dev->reg_state == NETREG_UNREGISTERING) {
                        __skb_unlink(skb, &sd->input_pkt_queue);
-                       kfree_skb(skb);
+                       __skb_queue_tail(&sd->tofree_queue, skb);
                        input_queue_head_incr(sd);
                }
        }
@@ -4639,11 +4655,14 @@ static void flush_backlog(struct work_struct *work)
        skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
                if (skb->dev->reg_state == NETREG_UNREGISTERING) {
                        __skb_unlink(skb, &sd->process_queue);
-                       kfree_skb(skb);
+                       __skb_queue_tail(&sd->tofree_queue, skb);
                        input_queue_head_incr(sd);
                }
        }
+       if (!skb_queue_empty(&sd->tofree_queue))
+               raise_softirq_irqoff(NET_RX_SOFTIRQ);
        local_bh_enable();
+
 }
 
 static void flush_all_backlogs(void)
@@ -5153,12 +5172,14 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
                sd->rps_ipi_list = NULL;
 
                local_irq_enable();
+               preempt_check_resched_rt();
 
                /* Send pending IPI's to kick RPS processing on remote cpus. */
                net_rps_send_ipi(remsd);
        } else
 #endif
                local_irq_enable();
+       preempt_check_resched_rt();
 }
 
 static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
@@ -5188,7 +5209,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
        while (again) {
                struct sk_buff *skb;
 
+               local_irq_disable();
                while ((skb = __skb_dequeue(&sd->process_queue))) {
+                       local_irq_enable();
                        rcu_read_lock();
                        __netif_receive_skb(skb);
                        rcu_read_unlock();
@@ -5196,9 +5219,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
                        if (++work >= quota)
                                return work;
 
+                       local_irq_disable();
                }
 
-               local_irq_disable();
                rps_lock(sd);
                if (skb_queue_empty(&sd->input_pkt_queue)) {
                        /*
@@ -5236,6 +5259,7 @@ void __napi_schedule(struct napi_struct *n)
        local_irq_save(flags);
        ____napi_schedule(this_cpu_ptr(&softnet_data), n);
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(__napi_schedule);
 
@@ -5272,6 +5296,7 @@ bool napi_schedule_prep(struct napi_struct *n)
 }
 EXPORT_SYMBOL(napi_schedule_prep);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * __napi_schedule_irqoff - schedule for receive
  * @n: entry to schedule
@@ -5283,6 +5308,7 @@ void __napi_schedule_irqoff(struct napi_struct *n)
        ____napi_schedule(this_cpu_ptr(&softnet_data), n);
 }
 EXPORT_SYMBOL(__napi_schedule_irqoff);
+#endif
 
 bool napi_complete_done(struct napi_struct *n, int work_done)
 {
@@ -5637,13 +5663,21 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
        unsigned long time_limit = jiffies +
                usecs_to_jiffies(netdev_budget_usecs);
        int budget = netdev_budget;
+       struct sk_buff_head tofree_q;
+       struct sk_buff *skb;
        LIST_HEAD(list);
        LIST_HEAD(repoll);
 
+       __skb_queue_head_init(&tofree_q);
+
        local_irq_disable();
+       skb_queue_splice_init(&sd->tofree_queue, &tofree_q);
        list_splice_init(&sd->poll_list, &list);
        local_irq_enable();
 
+       while ((skb = __skb_dequeue(&tofree_q)))
+               kfree_skb(skb);
+
        for (;;) {
                struct napi_struct *n;
 
@@ -5673,7 +5707,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
        list_splice_tail(&repoll, &list);
        list_splice(&list, &sd->poll_list);
        if (!list_empty(&sd->poll_list))
-               __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+               __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ);
 
        net_rps_action_and_irq_enable(sd);
 out:
@@ -7502,7 +7536,7 @@ static void netdev_init_one_queue(struct net_device *dev,
        /* Initialize queue lock */
        spin_lock_init(&queue->_xmit_lock);
        netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
-       queue->xmit_lock_owner = -1;
+       netdev_queue_clear_owner(queue);
        netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
        queue->dev = dev;
 #ifdef CONFIG_BQL
@@ -8442,6 +8476,7 @@ static int dev_cpu_dead(unsigned int oldcpu)
 
        raise_softirq_irqoff(NET_TX_SOFTIRQ);
        local_irq_enable();
+       preempt_check_resched_rt();
 
 #ifdef CONFIG_RPS
        remsd = oldsd->rps_ipi_list;
@@ -8455,10 +8490,13 @@ static int dev_cpu_dead(unsigned int oldcpu)
                netif_rx_ni(skb);
                input_queue_head_incr(oldsd);
        }
-       while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
+       while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
                netif_rx_ni(skb);
                input_queue_head_incr(oldsd);
        }
+       while ((skb = __skb_dequeue(&oldsd->tofree_queue))) {
+               kfree_skb(skb);
+       }
 
        return 0;
 }
@@ -8762,8 +8800,9 @@ static int __init net_dev_init(void)
 
                INIT_WORK(flush, flush_backlog);
 
-               skb_queue_head_init(&sd->input_pkt_queue);
-               skb_queue_head_init(&sd->process_queue);
+               skb_queue_head_init_raw(&sd->input_pkt_queue);
+               skb_queue_head_init_raw(&sd->process_queue);
+               skb_queue_head_init_raw(&sd->tofree_queue);
                INIT_LIST_HEAD(&sd->poll_list);
                sd->output_queue_tailp = &sd->output_queue;
 #ifdef CONFIG_RPS
diff --git a/net/core/filter.c b/net/core/filter.c
index d5158a10ac8f..ad96ec78f7b8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1696,7 +1696,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 {
        int ret;
 
-       if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
+       if (unlikely(xmit_rec_read() > XMIT_RECURSION_LIMIT)) {
                net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
                kfree_skb(skb);
                return -ENETDOWN;
@@ -1704,9 +1704,9 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 
        skb->dev = dev;
 
-       __this_cpu_inc(xmit_recursion);
+       xmit_rec_inc();
        ret = dev_queue_xmit(skb);
-       __this_cpu_dec(xmit_recursion);
+       xmit_rec_dec();
 
        return ret;
 }
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 7f980bd7426e..7250106015ef 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -46,7 +46,7 @@
 struct net_rate_estimator {
        struct gnet_stats_basic_packed  *bstats;
        spinlock_t              *stats_lock;
-       seqcount_t              *running;
+       net_seqlock_t           *running;
        struct gnet_stats_basic_cpu __percpu *cpu_bstats;
        u8                      ewma_log;
        u8                      intvl_log; /* period : (250ms << intvl_log) */
@@ -129,7 +129,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
                      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
                      struct net_rate_estimator __rcu **rate_est,
                      spinlock_t *stats_lock,
-                     seqcount_t *running,
+                     net_seqlock_t *running,
                      struct nlattr *opt)
 {
        struct gnet_estimator *parm = nla_data(opt);
@@ -222,7 +222,7 @@ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
                          struct gnet_stats_basic_cpu __percpu *cpu_bstats,
                          struct net_rate_estimator __rcu **rate_est,
                          spinlock_t *stats_lock,
-                         seqcount_t *running, struct nlattr *opt)
+                         net_seqlock_t *running, struct nlattr *opt)
 {
        return gen_new_estimator(bstats, cpu_bstats, rate_est,
                                 stats_lock, running, opt);
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 441c04adedba..07f9a6a1f8e4 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -142,7 +142,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
 }
 
 void
-__gnet_stats_copy_basic(const seqcount_t *running,
+__gnet_stats_copy_basic(net_seqlock_t *running,
                        struct gnet_stats_basic_packed *bstats,
                        struct gnet_stats_basic_cpu __percpu *cpu,
                        struct gnet_stats_basic_packed *b)
@@ -155,10 +155,10 @@ __gnet_stats_copy_basic(const seqcount_t *running,
        }
        do {
                if (running)
-                       seq = read_seqcount_begin(running);
+                       seq = net_seq_begin(running);
                bstats->bytes = b->bytes;
                bstats->packets = b->packets;
-       } while (running && read_seqcount_retry(running, seq));
+       } while (running && net_seq_retry(running, seq));
 }
 EXPORT_SYMBOL(__gnet_stats_copy_basic);
 
@@ -176,7 +176,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic);
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_basic(const seqcount_t *running,
+gnet_stats_copy_basic(net_seqlock_t *running,
                      struct gnet_dump *d,
                      struct gnet_stats_basic_cpu __percpu *cpu,
                      struct gnet_stats_basic_packed *b)
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 6e1e10ff433a..c1ae4075e0ed 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2252,7 +2252,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
        s64 remaining;
        struct hrtimer_sleeper t;
 
-       hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+       hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS,
+                                     current);
        hrtimer_set_expires(&t.timer, spin_until);
 
        remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer));
@@ -2267,7 +2268,6 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
                } while (ktime_compare(end_time, spin_until) < 0);
        } else {
                /* see do_nanosleep */
-               hrtimer_init_sleeper(&t, current);
                do {
                        set_current_state(TASK_INTERRUPTIBLE);
                        hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9f80b947f53b..c0f23b8dcfc6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -63,6 +63,7 @@
 #include <linux/errqueue.h>
 #include <linux/prefetch.h>
 #include <linux/if_vlan.h>
+#include <linux/locallock.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -330,6 +331,8 @@ struct napi_alloc_cache {
 
 static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
 static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
+static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock);
+static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock);
 
 static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
@@ -337,10 +340,10 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
        unsigned long flags;
        void *data;
 
-       local_irq_save(flags);
+       local_lock_irqsave(netdev_alloc_lock, flags);
        nc = this_cpu_ptr(&netdev_alloc_cache);
        data = page_frag_alloc(nc, fragsz, gfp_mask);
-       local_irq_restore(flags);
+       local_unlock_irqrestore(netdev_alloc_lock, flags);
        return data;
 }
 
@@ -359,9 +362,13 @@ EXPORT_SYMBOL(netdev_alloc_frag);
 
 static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
-       struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+       struct napi_alloc_cache *nc;
+       void *data;
 
-       return page_frag_alloc(&nc->page, fragsz, gfp_mask);
+       nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
+       data =  page_frag_alloc(&nc->page, fragsz, gfp_mask);
+       put_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
+       return data;
 }
 
 void *napi_alloc_frag(unsigned int fragsz)
@@ -408,13 +415,13 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
        if (sk_memalloc_socks())
                gfp_mask |= __GFP_MEMALLOC;
 
-       local_irq_save(flags);
+       local_lock_irqsave(netdev_alloc_lock, flags);
 
        nc = this_cpu_ptr(&netdev_alloc_cache);
        data = page_frag_alloc(nc, len, gfp_mask);
        pfmemalloc = nc->pfmemalloc;
 
-       local_irq_restore(flags);
+       local_unlock_irqrestore(netdev_alloc_lock, flags);
 
        if (unlikely(!data))
                return NULL;
@@ -455,9 +462,10 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
                                 gfp_t gfp_mask)
 {
-       struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+       struct napi_alloc_cache *nc;
        struct sk_buff *skb;
        void *data;
+       bool pfmemalloc;
 
        len += NET_SKB_PAD + NET_IP_ALIGN;
 
@@ -475,7 +483,10 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
        if (sk_memalloc_socks())
                gfp_mask |= __GFP_MEMALLOC;
 
+       nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
        data = page_frag_alloc(&nc->page, len, gfp_mask);
+       pfmemalloc = nc->page.pfmemalloc;
+       put_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
        if (unlikely(!data))
                return NULL;
 
@@ -486,7 +497,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
        }
 
        /* use OR instead of assignment to avoid clearing of bits in mask */
-       if (nc->page.pfmemalloc)
+       if (pfmemalloc)
                skb->pfmemalloc = 1;
        skb->head_frag = 1;
 
@@ -718,23 +729,26 @@ void __consume_stateless_skb(struct sk_buff *skb)
 
 void __kfree_skb_flush(void)
 {
-       struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+       struct napi_alloc_cache *nc;
 
+       nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
        /* flush skb_cache if containing objects */
        if (nc->skb_count) {
                kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count,
                                     nc->skb_cache);
                nc->skb_count = 0;
        }
+       put_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
 }
 
 static inline void _kfree_skb_defer(struct sk_buff *skb)
 {
-       struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+       struct napi_alloc_cache *nc;
 
        /* drop skb->head and call any destructors for packet */
        skb_release_all(skb);
 
+       nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
        /* record skb to CPU local list */
        nc->skb_cache[nc->skb_count++] = skb;
 
@@ -749,6 +763,7 @@ static inline void _kfree_skb_defer(struct sk_buff *skb)
                                     nc->skb_cache);
                nc->skb_count = 0;
        }
+       put_locked_var(napi_alloc_cache_lock, napi_alloc_cache);
 }
 void __kfree_skb_defer(struct sk_buff *skb)
 {
diff --git a/net/core/sock.c b/net/core/sock.c
index 68d08ed5521e..ee242ff5d4b1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2757,12 +2757,11 @@ void lock_sock_nested(struct sock *sk, int subclass)
        if (sk->sk_lock.owned)
                __lock_sock(sk);
        sk->sk_lock.owned = 1;
-       spin_unlock(&sk->sk_lock.slock);
+       spin_unlock_bh(&sk->sk_lock.slock);
        /*
         * The sk_lock has mutex_lock() semantics here:
         */
        mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
-       local_bh_enable();
 }
 EXPORT_SYMBOL(lock_sock_nested);
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 3c1570d3e22f..0310ea93f877 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -77,6 +77,7 @@
 #include <linux/string.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/slab.h>
+#include <linux/locallock.h>
 #include <net/snmp.h>
 #include <net/ip.h>
 #include <net/route.h>
@@ -204,6 +205,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
  *
  *     On SMP we have one ICMP socket per-cpu.
  */
+static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock);
+
 static struct sock *icmp_sk(struct net *net)
 {
        return *this_cpu_ptr(net->ipv4.icmp_sk);
@@ -214,12 +217,16 @@ static inline struct sock *icmp_xmit_lock(struct net *net)
 {
        struct sock *sk;
 
+       if (!local_trylock(icmp_sk_lock))
+               return NULL;
+
        sk = icmp_sk(net);
 
        if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
                /* This can happen if the output path signals a
                 * dst_link_failure() for an outgoing ICMP packet.
                 */
+               local_unlock(icmp_sk_lock);
                return NULL;
        }
        return sk;
@@ -228,6 +235,7 @@ static inline struct sock *icmp_xmit_lock(struct net *net)
 static inline void icmp_xmit_unlock(struct sock *sk)
 {
        spin_unlock(&sk->sk_lock.slock);
+       local_unlock(icmp_sk_lock);
 }
 
 int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 31b34c0c2d5f..851f241e70b5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -62,6 +62,7 @@
 #include <linux/init.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/locallock.h>
 
 #include <net/net_namespace.h>
 #include <net/icmp.h>
@@ -580,6 +581,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_v4_send_check);
 
+static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock);
 /*
  *     This routine will send an RST to the other tcp.
  *
@@ -710,6 +712,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
        arg.tos = ip_hdr(skb)->tos;
        arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
        local_bh_disable();
+       local_lock(tcp_sk_lock);
        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                              ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
@@ -717,6 +720,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 
        __TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
        __TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
+       local_unlock(tcp_sk_lock);
        local_bh_enable();
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -796,12 +800,14 @@ static void tcp_v4_send_ack(const struct sock *sk,
        arg.tos = tos;
        arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
        local_bh_disable();
+       local_lock(tcp_sk_lock);
        ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                              ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                              &arg, arg.iov[0].iov_len);
 
        __TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
+       local_unlock(tcp_sk_lock);
        local_bh_enable();
 }
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index dddd498e1338..8f39b8162df8 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4252,7 +4252,7 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
        struct ieee80211_supported_band *sband;
        struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 
-       WARN_ON_ONCE(softirq_count() == 0);
+       WARN_ON_ONCE_NONRT(softirq_count() == 0);
 
        if (WARN_ON(status->band >= NUM_NL80211_BANDS))
                goto drop;
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 52cd2901a097..c63e937b6676 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -21,6 +21,7 @@
 #include <linux/inetdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/mutex.h>
+#include <linux/locallock.h>
 #include <linux/mm.h>
 #include <linux/rcupdate.h>
 #include <net/net_namespace.h>
@@ -28,6 +29,11 @@
 
 #include "nf_internals.h"
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+DEFINE_LOCAL_IRQ_LOCK(xt_write_lock);
+EXPORT_PER_CPU_SYMBOL(xt_write_lock);
+#endif
+
 static DEFINE_MUTEX(afinfo_mutex);
 
 const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8d1a7c900393..f1f56be3b061 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -63,6 +63,7 @@
 #include <linux/if_packet.h>
 #include <linux/wireless.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -707,7 +708,7 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data)
        if (BLOCK_NUM_PKTS(pbd)) {
                while (atomic_read(&pkc->blk_fill_in_prog)) {
                        /* Waiting for skb_copy_bits to finish... */
-                       cpu_relax();
+                       cpu_chill();
                }
        }
 
@@ -969,7 +970,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc,
                if (!(status & TP_STATUS_BLK_TMO)) {
                        while (atomic_read(&pkc->blk_fill_in_prog)) {
                                /* Waiting for skb_copy_bits to finish... */
-                               cpu_relax();
+                               cpu_chill();
                        }
                }
                prb_close_block(pkc, pbd, po, status);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 9a3c54e659e9..2a95f1d587ac 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/rculist.h>
 #include <linux/llist.h>
+#include <linux/delay.h>
 
 #include "rds_single_path.h"
 #include "ib_mr.h"
@@ -210,7 +211,7 @@ static inline void wait_clean_list_grace(void)
        for_each_online_cpu(cpu) {
                flag = &per_cpu(clean_list_grace, cpu);
                while (test_bit(CLEAN_LIST_BUSY_BIT, flag))
-                       cpu_relax();
+                       cpu_chill();
        }
 }
 
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index e9f428351293..c4479afe8ae7 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -19,9 +19,6 @@
 #include <keys/rxrpc-type.h>
 #include "ar-internal.h"
 
-static LIST_HEAD(rxrpc_security_methods);
-static DECLARE_RWSEM(rxrpc_security_sem);
-
 static const struct rxrpc_security *rxrpc_security_types[] = {
        [RXRPC_SECURITY_NONE]   = &rxrpc_no_security,
 #ifdef CONFIG_RXKAD
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index cd69aa067543..73348ac5019f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1081,7 +1081,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
                        rcu_assign_pointer(sch->stab, stab);
                }
                if (tca[TCA_RATE]) {
-                       seqcount_t *running;
+                       net_seqlock_t *running;
 
                        err = -EOPNOTSUPP;
                        if (sch->flags & TCQ_F_MQROOT)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 79549baf5804..341f7895659c 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -429,7 +429,11 @@ struct Qdisc noop_qdisc = {
        .ops            =       &noop_qdisc_ops,
        .q.lock         =       __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
        .dev_queue      =       &noop_netdev_queue,
+#ifdef CONFIG_PREEMPT_RT_BASE
+       .running        =       __SEQLOCK_UNLOCKED(noop_qdisc.running),
+#else
        .running        =       SEQCNT_ZERO(noop_qdisc.running),
+#endif
        .busylock       =       __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
 };
 EXPORT_SYMBOL(noop_qdisc);
@@ -628,9 +632,17 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
        lockdep_set_class(&sch->busylock,
                          dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+       seqlock_init(&sch->running);
+       lockdep_set_class(&sch->running.seqcount,
+                         dev->qdisc_running_key ?: &qdisc_running_key);
+       lockdep_set_class(&sch->running.lock,
+                         dev->qdisc_running_key ?: &qdisc_running_key);
+#else
        seqcount_init(&sch->running);
        lockdep_set_class(&sch->running,
                          dev->qdisc_running_key ?: &qdisc_running_key);
+#endif
 
        sch->ops = ops;
        sch->enqueue = ops->enqueue;
@@ -933,7 +945,7 @@ void dev_deactivate_many(struct list_head *head)
        /* Wait for outstanding qdisc_run calls. */
        list_for_each_entry(dev, head, close_list) {
                while (some_qdisc_is_busy(dev))
-                       yield();
+                       msleep(1);
                /* The new qdisc is assigned at this point so we can safely
                 * unwind stale skb lists and qdisc statistics
                 */
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index d16a8b423c20..cedaf909eb97 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -396,7 +396,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
                goto out;
        }
 
-       cpu = get_cpu();
+       cpu = get_cpu_light();
        pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
 
        atomic_long_inc(&pool->sp_stats.packets);
@@ -432,7 +432,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 
                atomic_long_inc(&pool->sp_stats.threads_woken);
                wake_up_process(rqstp->rq_task);
-               put_cpu();
+               put_cpu_light();
                goto out;
        }
        rcu_read_unlock();
@@ -453,7 +453,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt)
                goto redo_search;
        }
        rqstp = NULL;
-       put_cpu();
+       put_cpu_light();
 out:
        trace_svc_xprt_do_enqueue(xprt, rqstp);
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 6c4ec69e11a0..77f52dc790ec 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -427,7 +427,7 @@ static void xfrm_put_mode(struct xfrm_mode *mode)
 
 static void xfrm_state_gc_destroy(struct xfrm_state *x)
 {
-       tasklet_hrtimer_cancel(&x->mtimer);
+       hrtimer_cancel(&x->mtimer);
        del_timer_sync(&x->rtimer);
        kfree(x->aead);
        kfree(x->aalg);
@@ -472,8 +472,8 @@ static void xfrm_state_gc_task(struct work_struct *work)
 
 static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
-       struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
-       struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
+       struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer);
+       enum hrtimer_restart ret = HRTIMER_NORESTART;
        unsigned long now = get_seconds();
        long next = LONG_MAX;
        int warn = 0;
@@ -537,7 +537,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
                km_state_expired(x, 0, 0);
 resched:
        if (next != LONG_MAX) {
-               tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
+               hrtimer_forward_now(&x->mtimer, ktime_set(next, 0));
+               ret = HRTIMER_RESTART;
        }
 
        goto out;
@@ -554,7 +555,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 
 out:
        spin_unlock(&x->lock);
-       return HRTIMER_NORESTART;
+       return ret;
 }
 
 static void xfrm_replay_timer_handler(unsigned long data);
@@ -573,8 +574,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
                INIT_HLIST_NODE(&x->bydst);
                INIT_HLIST_NODE(&x->bysrc);
                INIT_HLIST_NODE(&x->byspi);
-               tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
-                                       CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
+               hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
+               x->mtimer.function = xfrm_timer_handler;
                setup_timer(&x->rtimer, xfrm_replay_timer_handler,
                                (unsigned long)x);
                x->curlft.add_time = get_seconds();
@@ -1031,7 +1032,9 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
                                hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
                        }
                        x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
-                       tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+                       hrtimer_start(&x->mtimer,
+                                     ktime_set(net->xfrm.sysctl_acq_expires, 0),
+                                     HRTIMER_MODE_REL_SOFT);
                        net->xfrm.state_num++;
                        xfrm_hash_grow_check(net, x->bydst.next != NULL);
                        spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -1142,7 +1145,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
                hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
        }
 
-       tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+       hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
        if (x->replay_maxage)
                mod_timer(&x->rtimer, jiffies + x->replay_maxage);
 
@@ -1246,7 +1249,9 @@ static struct xfrm_state *__find_acq_core(struct net *net,
                x->mark.m = m->m;
                x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
                xfrm_state_hold(x);
-               tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+               hrtimer_start(&x->mtimer,
+                             ktime_set(net->xfrm.sysctl_acq_expires, 0),
+                             HRTIMER_MODE_REL_SOFT);
                list_add(&x->km.all, &net->xfrm.state_all);
                hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
                h = xfrm_src_hash(net, daddr, saddr, family);
@@ -1546,7 +1551,8 @@ int xfrm_state_update(struct xfrm_state *x)
                memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
                x1->km.dying = 0;
 
-               tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+               hrtimer_start(&x1->mtimer, ktime_set(1, 0),
+                             HRTIMER_MODE_REL_SOFT);
                if (x1->curlft.use_time)
                        xfrm_state_check_expire(x1);
 
@@ -1570,7 +1576,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
        if (x->curlft.bytes >= x->lft.hard_byte_limit ||
            x->curlft.packets >= x->lft.hard_packet_limit) {
                x->km.state = XFRM_STATE_EXPIRED;
-               tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL);
+               hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT);
                return -EINVAL;
        }
 
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
index 5522692100ba..8b4be8e1802a 100644
--- a/samples/trace_events/trace-events-sample.c
+++ b/samples/trace_events/trace-events-sample.c
@@ -33,7 +33,7 @@ static void simple_thread_func(int cnt)
 
        /* Silly tracepoints */
        trace_foo_bar("hello", cnt, array, random_strings[len],
-                     &current->cpus_allowed);
+                     current->cpus_ptr);
 
        trace_foo_with_template_simple("HELLO", cnt);
 
diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
index 959199c3147e..3e68004ed345 100755
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -5,7 +5,8 @@ TARGET=$1
 ARCH=$2
 SMP=$3
 PREEMPT=$4
-CC=$5
+RT=$5
+CC=$6
 
 vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
 
@@ -58,6 +59,7 @@ UTS_VERSION="#$VERSION"
 CONFIG_FLAGS=""
 if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
 if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
+if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi
 UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP"
 
 # Truncate to maximum length
diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h
index 05fb3305671e..b26c16b02662 100644
--- a/security/apparmor/include/path.h
+++ b/security/apparmor/include/path.h
@@ -39,9 +39,10 @@ struct aa_buffers {
 };
 
 #include <linux/percpu.h>
-#include <linux/preempt.h>
+#include <linux/locallock.h>
 
 DECLARE_PER_CPU(struct aa_buffers, aa_buffers);
+DECLARE_LOCAL_IRQ_LOCK(aa_buffers_lock);
 
 #define COUNT_ARGS(X...) COUNT_ARGS_HELPER(, ##X, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 #define COUNT_ARGS_HELPER(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, n, X...) n
@@ -55,12 +56,24 @@ DECLARE_PER_CPU(struct aa_buffers, aa_buffers);
 
 #define for_each_cpu_buffer(I) for ((I) = 0; (I) < MAX_PATH_BUFFERS; (I)++)
 
-#ifdef CONFIG_DEBUG_PREEMPT
+#ifdef CONFIG_PREEMPT_RT_BASE
+
+static inline void AA_BUG_PREEMPT_ENABLED(const char *s)
+{
+       struct local_irq_lock *lv;
+
+       lv = this_cpu_ptr(&aa_buffers_lock);
+       WARN_ONCE(lv->owner != current,
+                 "__get_buffer without aa_buffers_lock\n");
+}
+
+#elif defined(CONFIG_DEBUG_PREEMPT)
 #define AA_BUG_PREEMPT_ENABLED(X) AA_BUG(preempt_count() <= 0, X)
 #else
 #define AA_BUG_PREEMPT_ENABLED(X) /* nop */
 #endif
 
+
 #define __get_buffer(N) ({                                     \
        struct aa_buffers *__cpu_var; \
        AA_BUG_PREEMPT_ENABLED("__get_buffer without preempt disabled");  \
@@ -73,14 +86,14 @@ DECLARE_PER_CPU(struct aa_buffers, aa_buffers);
 
 #define get_buffers(X...)      \
 do {                           \
-       preempt_disable();      \
+       local_lock(aa_buffers_lock);    \
        __get_buffers(X);       \
 } while (0)
 
 #define put_buffers(X, Y...)   \
 do {                           \
        __put_buffers(X, Y);    \
-       preempt_enable();       \
+       local_unlock(aa_buffers_lock);  \
 } while (0)
 
 #endif /* __AA_PATH_H */
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 1346ee5be04f..aa7e4dee107b 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -44,7 +44,7 @@
 int apparmor_initialized;
 
 DEFINE_PER_CPU(struct aa_buffers, aa_buffers);
-
+DEFINE_LOCAL_IRQ_LOCK(aa_buffers_lock);
 
 /*
  * LSM hook functions
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index ab3bf36786b6..f0bb7c9aa4be 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -148,7 +148,7 @@ EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
 void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
 {
        if (!substream->pcm->nonatomic)
-               local_irq_disable();
+               local_irq_disable_nort();
        snd_pcm_stream_lock(substream);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
@@ -163,7 +163,7 @@ void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
 {
        snd_pcm_stream_unlock(substream);
        if (!substream->pcm->nonatomic)
-               local_irq_enable();
+               local_irq_enable_nort();
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq);
 
@@ -171,7 +171,7 @@ unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream)
 {
        unsigned long flags = 0;
        if (!substream->pcm->nonatomic)
-               local_irq_save(flags);
+               local_irq_save_nort(flags);
        snd_pcm_stream_lock(substream);
        return flags;
 }
@@ -189,7 +189,7 @@ void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
 {
        snd_pcm_stream_unlock(substream);
        if (!substream->pcm->nonatomic)
-               local_irq_restore(flags);
+               local_irq_restore_nort(flags);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore);
 
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index c0939a0164a6..549e014ecc0d 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -376,17 +376,9 @@ struct dummy_hrtimer_pcm {
        ktime_t period_time;
        atomic_t running;
        struct hrtimer timer;
-       struct tasklet_struct tasklet;
        struct snd_pcm_substream *substream;
 };
 
-static void dummy_hrtimer_pcm_elapsed(unsigned long priv)
-{
-       struct dummy_hrtimer_pcm *dpcm = (struct dummy_hrtimer_pcm *)priv;
-       if (atomic_read(&dpcm->running))
-               snd_pcm_period_elapsed(dpcm->substream);
-}
-
 static enum hrtimer_restart dummy_hrtimer_callback(struct hrtimer *timer)
 {
        struct dummy_hrtimer_pcm *dpcm;
@@ -394,7 +386,14 @@ static enum hrtimer_restart dummy_hrtimer_callback(struct hrtimer *timer)
        dpcm = container_of(timer, struct dummy_hrtimer_pcm, timer);
        if (!atomic_read(&dpcm->running))
                return HRTIMER_NORESTART;
-       tasklet_schedule(&dpcm->tasklet);
+       /*
+        * In cases of XRUN and draining, this calls .trigger to stop PCM
+        * substream.
+        */
+       snd_pcm_period_elapsed(dpcm->substream);
+       if (!atomic_read(&dpcm->running))
+               return HRTIMER_NORESTART;
+
        hrtimer_forward_now(timer, dpcm->period_time);
        return HRTIMER_RESTART;
 }
@@ -404,7 +403,7 @@ static int dummy_hrtimer_start(struct snd_pcm_substream *substream)
        struct dummy_hrtimer_pcm *dpcm = substream->runtime->private_data;
 
        dpcm->base_time = hrtimer_cb_get_time(&dpcm->timer);
-       hrtimer_start(&dpcm->timer, dpcm->period_time, HRTIMER_MODE_REL);
+       hrtimer_start(&dpcm->timer, dpcm->period_time, HRTIMER_MODE_REL_SOFT);
        atomic_set(&dpcm->running, 1);
        return 0;
 }
@@ -414,14 +413,14 @@ static int dummy_hrtimer_stop(struct snd_pcm_substream *substream)
        struct dummy_hrtimer_pcm *dpcm = substream->runtime->private_data;
 
        atomic_set(&dpcm->running, 0);
-       hrtimer_cancel(&dpcm->timer);
+       if (!hrtimer_callback_running(&dpcm->timer))
+               hrtimer_cancel(&dpcm->timer);
        return 0;
 }
 
 static inline void dummy_hrtimer_sync(struct dummy_hrtimer_pcm *dpcm)
 {
        hrtimer_cancel(&dpcm->timer);
-       tasklet_kill(&dpcm->tasklet);
 }
 
 static snd_pcm_uframes_t
@@ -466,12 +465,10 @@ static int dummy_hrtimer_create(struct snd_pcm_substream *substream)
        if (!dpcm)
                return -ENOMEM;
        substream->runtime->private_data = dpcm;
-       hrtimer_init(&dpcm->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       hrtimer_init(&dpcm->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
        dpcm->timer.function = dummy_hrtimer_callback;
        dpcm->substream = substream;
        atomic_set(&dpcm->running, 0);
-       tasklet_init(&dpcm->tasklet, dummy_hrtimer_pcm_elapsed,
-                    (unsigned long)dpcm);
        return 0;
 }
 
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index 6a4982d029bf..843c2b0d948e 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -70,6 +70,13 @@ disable_events() {
     echo 0 > events/enable
 }
 
+clear_synthetic_events() { # reset all current synthetic events
+    grep -v ^# synthetic_events |
+    while read line; do
+        echo "!$line" >> synthetic_events
+    done
+}
+
 initialize_ftrace() { # Reset ftrace to initial-state
 # As the initial state, ftrace will be set to nop tracer,
 # no events, no triggers, no filters, no function filters,
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
new file mode 100644
index 000000000000..786dce7e48be
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
@@ -0,0 +1,39 @@
+#!/bin/sh
+# description: event trigger - test extended error support
+
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo "Test extended error support"
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger &>/dev/null
+if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
+    fail "Failed to generate extended error in histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
new file mode 100644
index 000000000000..7fd5b4a8f060
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -0,0 +1,54 @@
+#!/bin/sh
+# description: event trigger - test field variable support
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test field variable support"
+
+echo 'wakeup_latency u64 lat; pid_t pid; int prio; char comm[16]' > synthetic_events
+echo 'hist:keys=comm:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_waking/trigger
+echo 'hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
+echo 'hist:keys=pid,prio,comm:vals=lat:sort=pid,prio' > events/synthetic/wakeup_latency/trigger
+
+ping localhost -c 3
+if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
+    fail "Failed to create inter-event histogram"
+fi
+
+if ! grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then
+    fail "Failed to create histogram with field variable"
+fi
+
+echo '!hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
+
+if grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then
+    fail "Failed to remove histogram with field variable"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
new file mode 100644
index 000000000000..c93dbe38b5df
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -0,0 +1,58 @@
+#!/bin/sh
+# description: event trigger - test inter-event combined histogram trigger
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+clear_synthetic_events
+
+echo "Test create synthetic event"
+
+echo 'waking_latency  u64 lat pid_t pid' > synthetic_events
+if [ ! -d events/synthetic/waking_latency ]; then
+    fail "Failed to create waking_latency synthetic event"
+fi
+
+echo "Test combined histogram"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_waking/trigger
+echo 'hist:keys=pid:waking_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).waking_latency($waking_lat,pid) if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=pid,lat:sort=pid,lat' > events/synthetic/waking_latency/trigger
+
+echo 'wakeup_latency u64 lat pid_t pid' >> synthetic_events
+echo 'hist:keys=pid:ts1=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts1:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid) if next_comm=="ping"' > events/sched/sched_switch/trigger
+
+echo 'waking+wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking+wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger
+echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking+wakeup_latency/trigger
+
+ping localhost -c 3
+if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
+    fail "Failed to create combined histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
new file mode 100644
index 000000000000..e84e7d048566
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -0,0 +1,50 @@
+#!/bin/sh
+# description: event trigger - test inter-event histogram trigger onmatch action
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+    fail "Failed to create wakeup_latency synthetic event"
+fi
+
+echo "Test create histogram for synthetic event"
+echo "Test histogram variables,simple expression support and onmatch action"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
+echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
+ping localhost -c 5
+if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
+    fail "Failed to create onmatch action inter-event histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
new file mode 100644
index 000000000000..7907d8aacde3
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -0,0 +1,50 @@
+#!/bin/sh
+# description: event trigger - test inter-event histogram trigger onmatch-onmax action
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+    fail "Failed to create wakeup_latency synthetic event"
+fi
+
+echo "Test create histogram for synthetic event"
+echo "Test histogram variables,simple expression support and onmatch-onmax action"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm):onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
+echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
+ping localhost -c 5
+if [ ! grep -q "ping" events/synthetic/wakeup_latency/hist -o ! grep -q "max:" events/sched/sched_switch/hist]; then
+    fail "Failed to create onmatch-onmax action inter-event histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
new file mode 100644
index 000000000000..38b7ed6242b2
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -0,0 +1,48 @@
+#!/bin/sh
+# description: event trigger - test inter-event histogram trigger onmax action
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+    fail "Failed to create wakeup_latency synthetic event"
+fi
+
+echo "Test onmax action"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_waking/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
+ping localhost -c 3
+if ! grep -q "max:" events/sched/sched_switch/hist; then
+    fail "Failed to create onmax action inter-event histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
new file mode 100644
index 000000000000..cef11377dcbd
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
@@ -0,0 +1,54 @@
+#!/bin/sh
+# description: event trigger - test synthetic event create remove
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+    fail "Failed to create wakeup_latency synthetic event"
+fi
+
+reset_trigger
+
+echo "Test create synthetic event with an error"
+echo 'wakeup_latency  u64 lat pid_t pid char' > synthetic_events > /dev/null
+if [ -d events/synthetic/wakeup_latency ]; then
+    fail "Created wakeup_latency synthetic event with an invalid format"
+fi
+
+reset_trigger
+
+echo "Test remove synthetic event"
+echo '!wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ -d events/synthetic/wakeup_latency ]; then
+    fail "Failed to delete wakeup_latency synthetic event"
+fi
+
+do_reset
+
+exit 0
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index d5f1d8364571..c09e04130bfe 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -69,7 +69,6 @@ static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
 
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
-       BUG_ON(preemptible());
        __this_cpu_write(kvm_arm_running_vcpu, vcpu);
 }
 
@@ -79,7 +78,6 @@ static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
  */
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
 {
-       BUG_ON(preemptible());
        return __this_cpu_read(kvm_arm_running_vcpu);
 }
 
@@ -653,7 +651,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
                 * involves poking the GIC, which must be done in a
                 * non-preemptible context.
                 */
-               preempt_disable();
+               migrate_disable();
 
                kvm_pmu_flush_hwstate(vcpu);
 
@@ -690,7 +688,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
                        kvm_pmu_sync_hwstate(vcpu);
                        kvm_timer_sync_hwstate(vcpu);
                        kvm_vgic_sync_hwstate(vcpu);
-                       preempt_enable();
+                       migrate_enable();
                        continue;
                }
 
@@ -745,7 +743,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
                kvm_vgic_sync_hwstate(vcpu);
 
-               preempt_enable();
+               migrate_enable();
 
                ret = handle_exit(vcpu, run, ret);
        }