The kzalloc() function has a 2-factor argument form, kcalloc(). This
patch replaces cases of:

        kzalloc(a * b, gfp)

with:
        kcalloc(a * b, gfp)

as well as handling cases of:

        kzalloc(a * b * c, gfp)

with:

        kzalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kzalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kzalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kzalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kzalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kzalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kzalloc
+ kcalloc
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kzalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kzalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kzalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kzalloc(sizeof(THING) * C2, ...)
|
  kzalloc(sizeof(TYPE) * C2, ...)
|
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(C1 * C2, ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	E1 * E2
+	E1, E2
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>

Split sparsemem initialisation from basic numa topology discovery.
Move the parsing earlier in boot, before pacas are allocated.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

We no longer allocate lppacas in an array, so this patch removes the
1kB static alignment for the structure, and enforces the PAPR
alignment requirements at allocation time. We can not reduce the 1kB
allocation size however, due to existing KVM hypervisors.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

When DLPAR removing a CPU, the unmapping of the cpu from a node in
unmap_cpu_from_node() should also invalidate the CPUs entry in the
numa_cpu_lookup_table. There is not a guarantee that on a subsequent
DLPAR add of the CPU the associativity will be the same and thus
could be in a different node. Invalidating the entry in the
numa_cpu_lookup_table causes the associativity to be read from the
device tree at the time of the add.

The current behavior of not invalidating the CPUs entry in the
numa_cpu_lookup_table can result in scenarios where the the topology
layout of CPUs in the partition does not match the device tree
or the topology reported by the HMC.

This bug looks like it was introduced in 2004 in the commit titled
"ppc64: cpu hotplug notifier for numa", which is 6b15e4e87e32 in the
linux-fullhist tree. Hence tag it for all stable releases.

Cc: stable@vger.kernel.org
Signed-off-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Reviewed-by: NTyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

On powerpc systems with shared configurations of CPUs and memory and
memoryless nodes at boot, an event ordering problem was observed on a
SLES12 build platforms with the hot-add of CPUs to the memoryless
nodes.

* The most common error occurred when the memory SLAB driver attempted
  to reference the memoryless node to which a CPU was being added
  before the kernel had finished initializing all of the data
  structures for the CPU and exited 'device_online' under
  DLPAR/hot-add.

  Normally the memoryless node would be initialized through the call
  path device_online ... arch_update_cpu_topology ... find_cpu_nid ...
  try_online_node. This patch ensures that the powerpc node will be
  initialized as early as possible, even if it was memoryless and
  CPU-less at the point when we are trying to hot-add a new CPU to it.
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Reviewed-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This patch fixes some problems encountered at runtime with
configurations that support memory-less nodes, or that hot-add CPUs
into nodes that are memoryless during system execution after boot. The
problems of interest include:

* Nodes known to powerpc to be memoryless at boot, but to have CPUs in
  them are allowed to be 'possible' and 'online'. Memory allocations
  for those nodes are taken from another node that does have memory
  until and if memory is hot-added to the node.

* Nodes which have no resources assigned at boot, but which may still
  be referenced subsequently by affinity or associativity attributes,
  are kept in the list of 'possible' nodes for powerpc. Hot-add of
  memory or CPUs to the system can reference these nodes and bring
  them online instead of redirecting the references to one of the set
  of nodes known to have memory at boot.

Note that this software operates under the context of CPU hotplug. We
are not doing memory hotplug in this code, but rather updating the
kernel's CPU topology (i.e. arch_update_cpu_topology /
numa_update_cpu_topology). We are initializing a node that may be used
by CPUs or memory before it can be referenced as invalid by a CPU
hotplug operation. CPU hotplug operations are protected by a range of
APIs including cpu_maps_update_begin/cpu_maps_update_done,
cpus_read/write_lock / cpus_read/write_unlock, device locks, and more.
Memory hotplug operations, including try_online_node, are protected by
mem_hotplug_begin/mem_hotplug_done, device locks, and more. In the
case of CPUs being hot-added to a previously memoryless node, the
try_online_node operation occurs wholly within the CPU locks with no
overlap. Using HMC hot-add/hot-remove operations, we have been able to
add and remove CPUs to any possible node without failures. HMC
operations involve a degree self-serialization, though.
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Reviewed-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

On powerpc systems which allow 'hot-add' of CPU or memory resources,
it may occur that the new resources are to be inserted into nodes that
were not used for these resources at bootup. In the kernel, any node
that is used must be defined and initialized. These empty nodes may
occur when,

* Dedicated vs. shared resources. Shared resources require information
  such as the VPHN hcall for CPU assignment to nodes. Associativity
  decisions made based on dedicated resource rules, such as
  associativity properties in the device tree, may vary from decisions
  made using the values returned by the VPHN hcall.

* memoryless nodes at boot. Nodes need to be defined as 'possible' at
  boot for operation with other code modules. Previously, the powerpc
  code would limit the set of possible nodes to those which have
  memory assigned at boot, and were thus online. Subsequent add/remove
  of CPUs or memory would only work with this subset of possible
  nodes.

* memoryless nodes with CPUs at boot. Due to the previous restriction
  on nodes, nodes that had CPUs but no memory were being collapsed
  into other nodes that did have memory at boot. In practice this
  meant that the node assignment presented by the runtime kernel
  differed from the affinity and associativity attributes presented by
  the device tree or VPHN hcalls. Nodes that might be known to the
  pHyp were not 'possible' in the runtime kernel because they did not
  have memory at boot.

This patch ensures that sufficient nodes are defined to support
configuration requirements after boot, as well as at boot. This patch
set fixes a couple of problems.

* Nodes known to powerpc to be memoryless at boot, but to have CPUs in
  them are allowed to be 'possible' and 'online'. Memory allocations
  for those nodes are taken from another node that does have memory
  until and if memory is hot-added to the node. * Nodes which have no
  resources assigned at boot, but which may still be referenced
  subsequently by affinity or associativity attributes, are kept in
  the list of 'possible' nodes for powerpc. Hot-add of memory or CPUs
  to the system can reference these nodes and bring them online
  instead of redirecting to one of the set of nodes that were known to
  have memory at boot.

This patch extracts the value of the lowest domain level (number of
allocable resources) from the device tree property
"ibm,max-associativity-domains" to use as the maximum number of nodes
to setup as possibly available in the system. This new setting will
override the instruction:

    nodes_and(node_possible_map, node_possible_map, node_online_map);

presently seen in the function arch/powerpc/mm/numa.c:initmem_init().

If the "ibm,max-associativity-domains" property is not present at
boot, no operation will be performed to define or enable additional
nodes, or enable the above 'nodes_and()'.
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Reviewed-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Update code in powerpc/numa.c to use the walk_drmem_lmbs()
routine instead of parsing the device tree directly. This is
in anticipation of introducing a new ibm,dynamic-memory-v2
property with a different format. This will allow the numa code
to use a single initialization routine per-LMB irregardless of
the device tree format.

Additionally, to support additional routines in numa.c that need
to look up LMB information, an late_init routine is added to drmem.c
to allocate the array of LMB information. This LMB array will provide
per-LMB information to separate the LMB data from the device tree
format.
Signed-off-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Look up the associativity arrays in of_drconf_to_nid_single when
deriving the nid for a LMB instead of having it passed in as a
parameter.
Signed-off-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Look up the device node for the usable memory property instead
of having it passed in as a parameter. This changes precedes an update
in which the calling routines for of_get_usable_memory() will not have
the device node pointer to pass in.
Signed-off-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Look up the device node for the associativity array property instead
of having it passed in as a parameter. This changes precedes an update
in which the calling routines for of_get_assoc_arrays() will not have
the device node pointer to pass in.
Signed-off-by: NNathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

powerpc/vphn: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources.  This patch
fixes an end-of-updates processing problem observed occasionally
in numa_update_cpu_topology().
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

powerpc/hotplug: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources.  During hotplug
CPU operations, this patch resets the timer on topology update work
function to a small value to better ensure that the CPU topology is
detected and configured sooner.
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

powerpc/vphn: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources.  This patch
updates the initialization checks to independently recognize PRRN
or VPHN support.
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

powerpc/vphn: On Power systems with shared configurations of CPUs
and memory, there are some issues with the association of additional
CPUs and memory to nodes when hot-adding resources.  This patch
corrects the currently broken capability to set the topology for
shared CPUs in LPARs.  At boot time for shared CPU lpars, the
topology for each CPU was being set to node zero.  Now when
numa_update_cpu_topology() is called appropriately, the Virtual
Processor Home Node (VPHN) capabilities information provided by the
pHyp allows the appropriate node in the shared configuration to be
selected for the CPU.
Signed-off-by: NMichael Bringmann <mwb@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

It turns out that not all paths calling arch_update_cpu_topology() hold
cpu_hotplug_lock, but that's OK because those paths can't race with
any concurrent hotplug events.

Warnings were reported with the following trace:

  lockdep_assert_cpus_held
  arch_update_cpu_topology
  sched_init_domains
  sched_init_smp
  kernel_init_freeable
  kernel_init
  ret_from_kernel_thread

Which is safe because it's called early in boot when hotplug is not
live yet.

And also this trace:

  lockdep_assert_cpus_held
  arch_update_cpu_topology
  partition_sched_domains
  cpuset_update_active_cpus
  sched_cpu_deactivate
  cpuhp_invoke_callback
  cpuhp_down_callbacks
  cpuhp_thread_fun
  smpboot_thread_fn
  kthread
  ret_from_kernel_thread

Which is safe because it's called as part of CPU hotplug, so although
we don't hold the CPU hotplug lock, there is another thread driving
the CPU hotplug operation which does hold the lock, and there is no
race.

Thanks to tglx for deciphering it for us.

Fixes: 3e401f7a ("powerpc: Only obtain cpu_hotplug_lock if called by rtasd")
Signed-off-by: NThiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This refactors the only users of init_timer_deferrable() to use
the new timer_setup() and from_timer(). Removes definition of
init_timer_deferrable().
Signed-off-by: NKees Cook <keescook@chromium.org>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: David S. Miller <davem@davemloft.net> # for networking parts
Acked-by: Sebastian Reichel <sre@kernel.org> # for drivers/hsi parts
Cc: linux-mips@linux-mips.org
Cc: Petr Mladek <pmladek@suse.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kalle Valo <kvalo@qca.qualcomm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: linux1394-devel@lists.sourceforge.net
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: linux-s390@vger.kernel.org
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: Wim Van Sebroeck <wim@iguana.be>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ursula Braun <ubraun@linux.vnet.ibm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Harish Patil <harish.patil@cavium.com>
Cc: Stephen Boyd <sboyd@codeaurora.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Manish Chopra <manish.chopra@cavium.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-pm@vger.kernel.org
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Mark Gross <mark.gross@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: linux-watchdog@vger.kernel.org
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-wireless@vger.kernel.org
Cc: Sebastian Reichel <sre@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Stefan Richter <stefanr@s5r6.in-berlin.de>
Cc: Michael Reed <mdr@sgi.com>
Cc: netdev@vger.kernel.org
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Link: https://lkml.kernel.org/r/1507159627-127660-6-git-send-email-keescook@chromium.org

Calling arch_update_cpu_topology from a CPU hotplug state machine callback
hits a deadlock because the function tries to get a read lock on
cpu_hotplug_lock while the state machine still holds a write lock on it.

Since all callers of arch_update_cpu_topology except rtasd already hold
cpu_hotplug_lock, this patch changes the function to use
stop_machine_cpuslocked and creates a separate function for rtasd which
still tries to obtain the lock.

Michael Bringmann investigated the bug and provided a detailed analysis
of the deadlock on this previous RFC for an alternate solution:
Signed-off-by: NThiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NMichael Ellerman <mpe@ellerman.id.au>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: Michael Bringmann <mwb@linux.vnet.ibm.com>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/1497996510-4032-1-git-send-email-bauerman@linux.vnet.ibm.com
Link: https://patchwork.ozlabs.org/patch/771293/

Generic core VM already prints these information in the log
buffer, hence there is no need for a second print. This just
removes the second print from arch powerpc NUMA init path.

Before the patch:

  $ dmesg | grep "Initmem"

  numa: Initmem setup node 0 [mem 0x00000000-0xffffffff]
  numa: Initmem setup node 1 [mem 0x100000000-0x1ffffffff]
  numa: Initmem setup node 2 [mem 0x200000000-0x2ffffffff]
  numa: Initmem setup node 3 [mem 0x300000000-0x3ffffffff]
  numa: Initmem setup node 4 [mem 0x400000000-0x4ffffffff]
  numa: Initmem setup node 5 [mem 0x500000000-0x5ffffffff]
  numa: Initmem setup node 6 [mem 0x600000000-0x6ffffffff]
  numa: Initmem setup node 7 [mem 0x700000000-0x7ffffffff]
  Initmem setup node 0 [mem 0x0000000000000000-0x00000000ffffffff]
  Initmem setup node 1 [mem 0x0000000100000000-0x00000001ffffffff]
  Initmem setup node 2 [mem 0x0000000200000000-0x00000002ffffffff]
  Initmem setup node 3 [mem 0x0000000300000000-0x00000003ffffffff]
  Initmem setup node 4 [mem 0x0000000400000000-0x00000004ffffffff]
  Initmem setup node 5 [mem 0x0000000500000000-0x00000005ffffffff]
  Initmem setup node 6 [mem 0x0000000600000000-0x00000006ffffffff]
  Initmem setup node 7 [mem 0x0000000700000000-0x00000007ffffffff]

After the patch just the latter set is printed.
Signed-off-by: NAnshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The generic implementation of of_node_to_nid() is EXPORT_SYMBOL, added
in commit 298535c0 ("of, numa: Add NUMA of binding
implementation.").

The powerpc implementation added in commit 953039c8 ("[PATCH]
powerpc: Allow devices to register with numa topology") is
EXPORT_SYMBOL_GPL.

This creates an inconsistency for of_node_to_nid() callers across
architectures.

Update the powerpc implementation to be exported consistently with the
generic implementation.
Signed-off-by: NShailendra Singh <shailendras@nvidia.com>
Reviewed-by: NAndy Ritger <aritger@nvidia.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Relax the check preventing us from hotplugging into an offline node.

This limitation was added in commit 482ec7c4 ("[PATCH] powerpc numa:
Support sparse online node map") to prevent adding resources to an
uninitialized node.

These days, there is no harm in doing so. The addition will actually
cause the node to be initialized and onlined; add_memory_resource()
calls hotadd_new_pgdat() (if necessary) and node_set_online().
Signed-off-by: NReza Arbab <arbab@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The flow of the main loop in parse_numa_properties() is overly
complicated. Simplify it to be less confusing and easier to read.
No functional change.

The end of the main loop in parse_numa_properties() looks like this:

	for_each_node_by_type(...) {
		...
		if (!condition) {
			if (--ranges)
				goto new_range;
			else
				continue;
		}

		statement();

		if (--ranges)
			goto new_range;
		/* else
		 *	continue; <- implicit, this is the end of the loop
		 */
	}

The only effect of !condition is to skip execution of statement(). This
can be rewritten in a simpler way:

	for_each_node_by_type(...) {
		...
		if (condition)
			statement();

		if (--ranges)
			goto new_range;
	}
Signed-off-by: NReza Arbab <arbab@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

When the state names got added a script was used to add the extra argument
to the calls. The script basically converted the state constant to a
string, but the cleanup to convert these strings into meaningful ones did
not happen.

Replace all the useless strings with 'subsys/xxx/yyy:state' strings which
are used in all the other places already.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Link: http://lkml.kernel.org/r/20161221192112.085444152@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Patch series "enable movable nodes on non-x86 configs", v7.

This patchset allows more configs to make use of movable nodes.  When
CONFIG_MOVABLE_NODE is selected, there are two ways to introduce such
nodes into the system:

1. Discover movable nodes at boot. Currently this is only possible on
   x86, but we will enable configs supporting fdt to do the same.

2. Hotplug and online all of a node's memory using online_movable. This
   is already possible on any config supporting memory hotplug, not
   just x86, but the Kconfig doesn't say so. We will fix that.

We'll also remove some cruft on power which would prevent (2).

This patch (of 5):

Remove the check which prevents us from hotplugging into an empty node.

The original commit b226e462 ("[PATCH] powerpc: don't add memory to
empty node/zone"), states that this was intended to be a temporary measure.
It is a workaround for an oops which no longer occurs.

Link: http://lkml.kernel.org/r/1479160961-25840-2-git-send-email-arbab@linux.vnet.ibm.comSigned-off-by: NReza Arbab <arbab@linux.vnet.ibm.com>
Reviewed-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NBalbir Singh <bsingharora@gmail.com>
Acked-by: NMichael Ellerman <mpe@ellerman.id.au>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Alistair Popple <apopple@au1.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bharata B Rao <bharata@linux.vnet.ibm.com>
Cc: Frank Rowand <frowand.list@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Stewart Smith <stewart@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

With recent update to printk, we get console output like below:

[    0.550639] Brought up 160 CPUs
[    0.550718] Node 0 CPUs:
[    0.550721]  0
[    0.550754] -39

[    0.550794] Node 1 CPUs:
[    0.550798]  40
[    0.550817] -79

[    0.550856] Node 16 CPUs:
[    0.550860]  80
[    0.550880] -119

[    0.550917] Node 17 CPUs:
[    0.550923]  120
[    0.550942] -159

Fix this by properly using pr_cont(), ie. KERN_CONT.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

At boot we dump the NUMA memory topology in dump_numa_memory_topology(),
at KERN_DEBUG level, resulting in output like:

  Node 0 Memory: 0x0-0x100000000
  Node 1 Memory: 0x100000000-0x200000000

Which is nice enough, but immediately after that we iterate over each
node and call setup_node_data(), which also prints out the node ranges,
at KERN_INFO, giving eg:

  numa: Initmem setup node 0 [mem 0x00000000-0xffffffff]
  numa: Initmem setup node 1 [mem 0x100000000-0x1ffffffff]

Additionally dump_numa_memory_topology() does not use KERN_CONT
correctly, resulting in split output lines on recent kernels.

So drop dump_numa_memory_topology() as superfluous chatter.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Acked-by: NBalbir Singh <bsingharora@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Install the callbacks via the state machine. On the boot cpu the callback is
invoked manually because cpuhp is not up yet and everything must be
preinitialized before additional CPUs are up.
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bharata B Rao <bharata@linux.vnet.ibm.com>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christophe Jaillet <christophe.jaillet@wanadoo.fr>
Cc: Anton Blanchard <anton@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160718140727.GA13132@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

memory_hotplug_max() uses hot_add_drconf_memory_max() to get maxmimum
addressable memory by referring to ibm,dyanamic-memory property. There
are three problems with the current approach:

1 hot_add_drconf_memory_max() assumes that ibm,dynamic-memory includes
  all the LMBs of the guest, but that is not true for PowerKVM which
  populates only DR LMBs (LMBs that can be hotplugged/removed) in that
  property.
2 hot_add_drconf_memory_max() multiplies lmb-size with lmb-count to arrive
  at the max possible address. Since ibm,dynamic-memory doesn't include
  RMA LMBs, the address thus obtained will be less than the actual max
  address. For example, if max possible memory size is 32G, with lmb-size
  of 256MB there can be 127 LMBs in ibm,dynamic-memory (1 LMB for RMA
  which won't be present here).  hot_add_drconf_memory_max() would then
  return the max addressable memory as 127 * 256MB = 31.75GB, the max
  address should have been 32G which is what ibm,lrdr-capacity shows.
3 In PowerKVM, there can be a gap between the end of boot time RAM and
  beginning of hotplug RAM area. So just multiplying lmb-count with
  lmb-size will not provide the correct max possible address for PowerKVM.

This patch fixes 1 by using ibm,lrdr-capacity property to return the max
addressable memory whenever the property is present. Then it fixes 2 & 3
by fetching the address of the last LMB in ibm,dynamic-memory property.

Fixes: cd34206e ("powerpc: Add memory_hotplug_max()")
Signed-off-by: NBharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Signed-off-by: NBharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: NDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

With the setup_nr_nodes(), we have already initialized
node_possible_map.  So it is safe to use for_each_node here.

There are many places in the kernel that use hardcoded 'for' loop with
nr_node_ids, because all other architectures have numa nodes populated
serially.  That should be reason we had maintained the same for
powerpc.

But, since sparse numa node ids possible on powerpc, we unnecessarily
allocate memory for non existent numa nodes.

For e.g., on a system with 0,1,16,17 as numa nodes nr_node_ids=18 and
we allocate memory for nodes 2-14.  This patch we allocate memory for
only existing numa nodes.

The patch is boot tested on a 4 node tuleta, confirming with printks
that it works as expected.
Signed-off-by: NRaghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Anton Blanchard <anton@samba.org>
Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

of_get_next_parent can be used to simplify the while() loop and
avoid the need of a temp variable.
Signed-off-by: NChristophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

In some situations, a NUMA guest that supports
ibm,dynamic-memory-reconfiguration node will end up having flat NUMA
distances between nodes. This is because of two problems in the
current code.

1) Different representations of associativity lists.

   There is an assumption about the associativity list in
   initialize_distance_lookup_table(). Associativity list has two forms:

   a) [cpu,memory]@x/ibm,associativity has following
      format:
           <N> <N integers>

   b) ibm,dynamic-reconfiguration-memory/ibm,associativity-lookup-arrays

           <M> <N> <M associativity lists each having N integers>
           M = the number of associativity lists
           N = the number of entries per associativity list

   Fix initialize_distance_lookup_table() so that it does not assume
   "case a". And update the caller to skip the length field before
   sending the associativity list.

2) Distance table not getting updated from drconf path.

   Node distance table will not get initialized in certain cases as
   ibm,dynamic-reconfiguration-memory path does not initialize the
   lookup table.

   Call initialize_distance_lookup_table() from drconf path with
   appropriate associativity list.
Reported-by: NBharata B Rao <bharata@linux.vnet.ibm.com>
Signed-off-by: NNikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Acked-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Raghu noticed an issue with excessive memory allocation on power with a
simple cgroup test, specifically, in mem_cgroup_css_alloc ->
for_each_node -> alloc_mem_cgroup_per_zone_info(), which ends up blowing
up the kmalloc-2048 slab (to the order of 200MB for 400 cgroup
directories).

The underlying issue is that NODES_SHIFT on power is 8 (256 NUMA nodes
possible), which defines node_possible_map, which in turn defines the
value of nr_node_ids in setup_nr_node_ids and the iteration of
for_each_node.

In practice, we never see a system with 256 NUMA nodes, and in fact, we
do not support node hotplug on power in the first place, so the nodes
that are online when we come up are the nodes that will be present for
the lifetime of this kernel. So let's, at least, drop the NUMA possible
map down to the online map at runtime. This is similar to what x86 does
in its initialization routines.

mem_cgroup_css_alloc should also be fixed to only iterate over
memory-populated nodes and handle hotplug, but that is a separate
change.
Signed-off-by: NNishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The goal behind this patch is to be able to write userland tests for the
VPHN parsing code.
Suggested-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The first argument to vphn_unpack_associativity() is a const long *, but the
parsing code expects __be64 values actually. Let's move the endian fixing
down for consistency.
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The number of values returned by the H_HOME_NODE_ASSOCIATIVITY h_call deserves
to be explicitly defined, for a better understanding of the code.
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The OF_RECONFIG notifier callback uses a different structure depending
on whether it is a node change or a property change. This is silly, and
not very safe. Rework the code to use the same data structure regardless
of the type of notifier.
Signed-off-by: NGrant Likely <grant.likely@linaro.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Cc: <linuxppc-dev@lists.ozlabs.org>

We did part of sparse initialisation in setup_arch and part in
initmem_init. Put them together.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Tested-by: NEmil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

At the moment we transition from the memblock alloctor to the bootmem
allocator. Gitting rid of the bootmem allocator removes a bunch of
complicated code (most of which I owe the dubious honour of being
responsible for writing).
Signed-off-by: NAnton Blanchard <anton@samba.org>
Tested-by: NEmil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

We received a report of warning in kernel/sched/core.c where the sched
group was NULL on an LPAR after a topology update. This seems to occur
because after the topology update has moved the CPUs, cpu_to_node is
returning the old value still, which ends up breaking the consistency of
the NUMA topology in the per-cpu maps. Ensure that we update the per-cpu
fields when we re-map CPUs.
Signed-off-by: NNishanth Aravamudan <nacc@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>