Merge ad57a1022f ("Merge tag 'exfat-for-5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/linkinjeon/exfat") into android-mainline

Steps on the way to 5.8-rc1.

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I4bc42f572167ea2f815688b4d1eb6124b6d260d4

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -486,6 +486,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
 		/sys/devices/system/cpu/vulnerabilities/mds
+		/sys/devices/system/cpu/vulnerabilities/srbds
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 Date:		January 2018

Documentation/admin-guide/cgroup-v2.rst

@@ -1170,6 +1170,13 @@ PAGE_SIZE multiple when read back.
 	Under certain circumstances, the usage may go over the limit
 	temporarily.
 
+	In default configuration regular 0-order allocations always
+	succeed unless OOM killer chooses current task as a victim.
+
+	Some kinds of allocations don't invoke the OOM killer.
+	Caller could retry them differently, return into userspace
+	as -ENOMEM or silently ignore in cases like disk readahead.
+
 	This is the ultimate protection mechanism.  As long as the
 	high limit is used and monitored properly, this limit's
 	utility is limited to providing the final safety net.
@@ -1226,17 +1233,9 @@ PAGE_SIZE multiple when read back.
 		The number of time the cgroup's memory usage was
 		reached the limit and allocation was about to fail.
 
-		Depending on context result could be invocation of OOM
-		killer and retrying allocation or failing allocation.
-
-		Failed allocation in its turn could be returned into
-		userspace as -ENOMEM or silently ignored in cases like
-		disk readahead.  For now OOM in memory cgroup kills
-		tasks iff shortage has happened inside page fault.
-
 		This event is not raised if the OOM killer is not
 		considered as an option, e.g. for failed high-order
-		allocations.
+		allocations or if caller asked to not retry attempts.
 
 	  oom_kill
 		The number of processes belonging to this cgroup

Documentation/admin-guide/dynamic-debug-howto.rst

@@ -13,6 +13,11 @@ kernel code to obtain additional kernel information.  Currently, if
 ``print_hex_dump_debug()``/``print_hex_dump_bytes()`` calls can be dynamically
 enabled per-callsite.
 
+If you do not want to enable dynamic debug globally (i.e. in some embedded
+system), you may set ``CONFIG_DYNAMIC_DEBUG_CORE`` as basic support of dynamic
+debug and add ``ccflags := -DDYNAMIC_DEBUG_MODULE`` into the Makefile of any
+modules which you'd like to dynamically debug later.
+
 If ``CONFIG_DYNAMIC_DEBUG`` is not set, ``print_hex_dump_debug()`` is just
 shortcut for ``print_hex_dump(KERN_DEBUG)``.
 

Documentation/admin-guide/hw-vuln/index.rst

@@ -14,3 +14,4 @@ are configurable at compile, boot or run time.
    mds
    tsx_async_abort
    multihit.rst
+   special-register-buffer-data-sampling.rst

Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst

@@ -0,0 +1,149 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+SRBDS - Special Register Buffer Data Sampling
+=============================================
+
+SRBDS is a hardware vulnerability that allows MDS :doc:`mds` techniques to
+infer values returned from special register accesses.  Special register
+accesses are accesses to off core registers.  According to Intel's evaluation,
+the special register reads that have a security expectation of privacy are
+RDRAND, RDSEED and SGX EGETKEY.
+
+When RDRAND, RDSEED and EGETKEY instructions are used, the data is moved
+to the core through the special register mechanism that is susceptible
+to MDS attacks.
+
+Affected processors
+--------------------
+Core models (desktop, mobile, Xeon-E3) that implement RDRAND and/or RDSEED may
+be affected.
+
+A processor is affected by SRBDS if its Family_Model and stepping is
+in the following list, with the exception of the listed processors
+exporting MDS_NO while Intel TSX is available yet not enabled. The
+latter class of processors are only affected when Intel TSX is enabled
+by software using TSX_CTRL_MSR otherwise they are not affected.
+
+  =============  ============  ========
+  common name    Family_Model  Stepping
+  =============  ============  ========
+  IvyBridge      06_3AH        All
+
+  Haswell        06_3CH        All
+  Haswell_L      06_45H        All
+  Haswell_G      06_46H        All
+
+  Broadwell_G    06_47H        All
+  Broadwell      06_3DH        All
+
+  Skylake_L      06_4EH        All
+  Skylake        06_5EH        All
+
+  Kabylake_L     06_8EH        <= 0xC
+  Kabylake       06_9EH        <= 0xD
+  =============  ============  ========
+
+Related CVEs
+------------
+
+The following CVE entry is related to this SRBDS issue:
+
+    ==============  =====  =====================================
+    CVE-2020-0543   SRBDS  Special Register Buffer Data Sampling
+    ==============  =====  =====================================
+
+Attack scenarios
+----------------
+An unprivileged user can extract values returned from RDRAND and RDSEED
+executed on another core or sibling thread using MDS techniques.
+
+
+Mitigation mechanism
+-------------------
+Intel will release microcode updates that modify the RDRAND, RDSEED, and
+EGETKEY instructions to overwrite secret special register data in the shared
+staging buffer before the secret data can be accessed by another logical
+processor.
+
+During execution of the RDRAND, RDSEED, or EGETKEY instructions, off-core
+accesses from other logical processors will be delayed until the special
+register read is complete and the secret data in the shared staging buffer is
+overwritten.
+
+This has three effects on performance:
+
+#. RDRAND, RDSEED, or EGETKEY instructions have higher latency.
+
+#. Executing RDRAND at the same time on multiple logical processors will be
+   serialized, resulting in an overall reduction in the maximum RDRAND
+   bandwidth.
+
+#. Executing RDRAND, RDSEED or EGETKEY will delay memory accesses from other
+   logical processors that miss their core caches, with an impact similar to
+   legacy locked cache-line-split accesses.
+
+The microcode updates provide an opt-out mechanism (RNGDS_MITG_DIS) to disable
+the mitigation for RDRAND and RDSEED instructions executed outside of Intel
+Software Guard Extensions (Intel SGX) enclaves. On logical processors that
+disable the mitigation using this opt-out mechanism, RDRAND and RDSEED do not
+take longer to execute and do not impact performance of sibling logical
+processors memory accesses. The opt-out mechanism does not affect Intel SGX
+enclaves (including execution of RDRAND or RDSEED inside an enclave, as well
+as EGETKEY execution).
+
+IA32_MCU_OPT_CTRL MSR Definition
+--------------------------------
+Along with the mitigation for this issue, Intel added a new thread-scope
+IA32_MCU_OPT_CTRL MSR, (address 0x123). The presence of this MSR and
+RNGDS_MITG_DIS (bit 0) is enumerated by CPUID.(EAX=07H,ECX=0).EDX[SRBDS_CTRL =
+9]==1. This MSR is introduced through the microcode update.
+
+Setting IA32_MCU_OPT_CTRL[0] (RNGDS_MITG_DIS) to 1 for a logical processor
+disables the mitigation for RDRAND and RDSEED executed outside of an Intel SGX
+enclave on that logical processor. Opting out of the mitigation for a
+particular logical processor does not affect the RDRAND and RDSEED mitigations
+for other logical processors.
+
+Note that inside of an Intel SGX enclave, the mitigation is applied regardless
+of the value of RNGDS_MITG_DS.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows control over the SRBDS mitigation at boot time
+with the option "srbds=".  The option for this is:
+
+  ============= =============================================================
+  off           This option disables SRBDS mitigation for RDRAND and RDSEED on
+                affected platforms.
+  ============= =============================================================
+
+SRBDS System Information
+-----------------------
+The Linux kernel provides vulnerability status information through sysfs.  For
+SRBDS this can be accessed by the following sysfs file:
+/sys/devices/system/cpu/vulnerabilities/srbds
+
+The possible values contained in this file are:
+
+ ============================== =============================================
+ Not affected                   Processor not vulnerable
+ Vulnerable                     Processor vulnerable and mitigation disabled
+ Vulnerable: No microcode       Processor vulnerable and microcode is missing
+                                mitigation
+ Mitigation: Microcode          Processor is vulnerable and mitigation is in
+                                effect.
+ Mitigation: TSX disabled       Processor is only vulnerable when TSX is
+                                enabled while this system was booted with TSX
+                                disabled.
+ Unknown: Dependent on
+ hypervisor status              Running on virtual guest processor that is
+                                affected but with no way to know if host
+                                processor is mitigated or vulnerable.
+ ============================== =============================================
+
+SRBDS Default mitigation
+------------------------
+This new microcode serializes processor access during execution of RDRAND,
+RDSEED ensures that the shared buffer is overwritten before it is released for
+reuse.  Use the "srbds=off" kernel command line to disable the mitigation for
+RDRAND and RDSEED.

Documentation/admin-guide/kdump/kdump.rst

@@ -521,6 +521,14 @@ will cause a kdump to occur at the panic() call.  In cases where a user wants
 to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1
 to achieve the same behaviour.
 
+Trigger Kdump on add_taint()
+============================
+
+The kernel parameter panic_on_taint facilitates a conditional call to panic()
+from within add_taint() whenever the value set in this bitmask matches with the
+bit flag being set by add_taint().
+This will cause a kdump to occur at the add_taint()->panic() call.
+
 Contact
 =======
 

Documentation/admin-guide/kernel-parameters.txt

@@ -1445,7 +1445,7 @@
 	hardlockup_all_cpu_backtrace=
 			[KNL] Should the hard-lockup detector generate
 			backtraces on all cpus.
-			Format: <integer>
+			Format: 0 | 1
 
 	hashdist=	[KNL,NUMA] Large hashes allocated during boot
 			are distributed across NUMA nodes.  Defaults on
@@ -1513,9 +1513,9 @@
 
 	hung_task_panic=
 			[KNL] Should the hung task detector generate panics.
-			Format: <integer>
+			Format: 0 | 1
 
-			A nonzero value instructs the kernel to panic when a
+			A value of 1 instructs the kernel to panic when a
 			hung task is detected. The default value is controlled
 			by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
 			option. The value selected by this boot parameter can
@@ -3447,6 +3447,19 @@
 			bit 4: print ftrace buffer
 			bit 5: print all printk messages in buffer
 
+	panic_on_taint=	Bitmask for conditionally calling panic() in add_taint()
+			Format: <hex>[,nousertaint]
+			Hexadecimal bitmask representing the set of TAINT flags
+			that will cause the kernel to panic when add_taint() is
+			called with any of the flags in this set.
+			The optional switch "nousertaint" can be utilized to
+			prevent userspace forced crashes by writing to sysctl
+			/proc/sys/kernel/tainted any flagset matching with the
+			bitmask set on panic_on_taint.
+			See Documentation/admin-guide/tainted-kernels.rst for
+			extra details on the taint flags that users can pick
+			to compose the bitmask to assign to panic_on_taint.
+
 	panic_on_warn	panic() instead of WARN().  Useful to cause kdump
 			on a WARN().
 
@@ -3715,6 +3728,8 @@
 				may put more devices in an IOMMU group.
 		force_floating	[S390] Force usage of floating interrupts.
 		nomio		[S390] Do not use MIO instructions.
+		norid		[S390] ignore the RID field and force use of
+				one PCI domain per PCI function
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
@@ -4652,9 +4667,9 @@
 
 	softlockup_panic=
 			[KNL] Should the soft-lockup detector generate panics.
-			Format: <integer>
+			Format: 0 | 1
 
-			A nonzero value instructs the soft-lockup detector
+			A value of 1 instructs the soft-lockup detector
 			to panic the machine when a soft-lockup occurs. It is
 			also controlled by the kernel.softlockup_panic sysctl
 			and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
@@ -4663,7 +4678,7 @@
 	softlockup_all_cpu_backtrace=
 			[KNL] Should the soft-lockup detector generate
 			backtraces on all cpus.
-			Format: <integer>
+			Format: 0 | 1
 
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/admin-guide/laptops/sonypi.rst
@@ -4822,6 +4837,26 @@
 			the kernel will oops in either "warn" or "fatal"
 			mode.
 
+	srbds=		[X86,INTEL]
+			Control the Special Register Buffer Data Sampling
+			(SRBDS) mitigation.
+
+			Certain CPUs are vulnerable to an MDS-like
+			exploit which can leak bits from the random
+			number generator.
+
+			By default, this issue is mitigated by
+			microcode.  However, the microcode fix can cause
+			the RDRAND and RDSEED instructions to become
+			much slower.  Among other effects, this will
+			result in reduced throughput from /dev/urandom.
+
+			The microcode mitigation can be disabled with
+			the following option:
+
+			off:    Disable mitigation and remove
+				performance impact to RDRAND and RDSEED
+
 	srcutree.counter_wrap_check [KNL]
 			Specifies how frequently to check for
 			grace-period sequence counter wrap for the
@@ -4956,6 +4991,15 @@
 
 	switches=	[HW,M68k]
 
+	sysctl.*=	[KNL]
+			Set a sysctl parameter, right before loading the init
+			process, as if the value was written to the respective
+			/proc/sys/... file. Both '.' and '/' are recognized as
+			separators. Unrecognized parameters and invalid values
+			are reported in the kernel log. Sysctls registered
+			later by a loaded module cannot be set this way.
+			Example: sysctl.vm.swappiness=40
+
 	sysfs.deprecated=0|1 [KNL]
 			Enable/disable old style sysfs layout for old udev
 			on older distributions. When this option is enabled

Documentation/admin-guide/mm/numa_memory_policy.rst

@@ -364,19 +364,19 @@ follows:
 
 2) for querying the policy, we do not need to take an extra reference on the
    target task's task policy nor vma policies because we always acquire the
-   task's mm's mmap_sem for read during the query.  The set_mempolicy() and
+   task's mm's mmap_lock for read during the query.  The set_mempolicy() and
-   mbind() APIs [see below] always acquire the mmap_sem for write when
+   mbind() APIs [see below] always acquire the mmap_lock for write when
    installing or replacing task or vma policies.  Thus, there is no possibility
    of a task or thread freeing a policy while another task or thread is
    querying it.
 
 3) Page allocation usage of task or vma policy occurs in the fault path where
-   we hold them mmap_sem for read.  Again, because replacing the task or vma
+   we hold them mmap_lock for read.  Again, because replacing the task or vma
-   policy requires that the mmap_sem be held for write, the policy can't be
+   policy requires that the mmap_lock be held for write, the policy can't be
    freed out from under us while we're using it for page allocation.
 
 4) Shared policies require special consideration.  One task can replace a
-   shared memory policy while another task, with a distinct mmap_sem, is
+   shared memory policy while another task, with a distinct mmap_lock, is
    querying or allocating a page based on the policy.  To resolve this
    potential race, the shared policy infrastructure adds an extra reference
    to the shared policy during lookup while holding a spin lock on the shared

Documentation/admin-guide/mm/userfaultfd.rst

@@ -33,7 +33,7 @@ memory ranges) provides two primary functionalities:
 The real advantage of userfaults if compared to regular virtual memory
 management of mremap/mprotect is that the userfaults in all their
 operations never involve heavyweight structures like vmas (in fact the
-``userfaultfd`` runtime load never takes the mmap_sem for writing).
+``userfaultfd`` runtime load never takes the mmap_lock for writing).
 
 Vmas are not suitable for page- (or hugepage) granular fault tracking
 when dealing with virtual address spaces that could span

Documentation/admin-guide/sysctl/kernel.rst

@@ -335,6 +335,20 @@ Path for the hotplug policy agent.
 Default value is "``/sbin/hotplug``".
 
 
+hung_task_all_cpu_backtrace:
+================
+
+If this option is set, the kernel will send an NMI to all CPUs to dump
+their backtraces when a hung task is detected. This file shows up if
+CONFIG_DETECT_HUNG_TASK and CONFIG_SMP are enabled.
+
+0: Won't show all CPUs backtraces when a hung task is detected.
+This is the default behavior.
+
+1: Will non-maskably interrupt all CPUs and dump their backtraces when
+a hung task is detected.
+
+
 hung_task_panic
 ===============
 
@@ -632,6 +646,22 @@ rate for each task.
 scanned for a given scan.
 
 
+oops_all_cpu_backtrace:
+================
+
+If this option is set, the kernel will send an NMI to all CPUs to dump
+their backtraces when an oops event occurs. It should be used as a last
+resort in case a panic cannot be triggered (to protect VMs running, for
+example) or kdump can't be collected. This file shows up if CONFIG_SMP
+is enabled.
+
+0: Won't show all CPUs backtraces when an oops is detected.
+This is the default behavior.
+
+1: Will non-maskably interrupt all CPUs and dump their backtraces when
+an oops event is detected.
+
+
 osrelease, ostype & version
 ===========================
 
@@ -1239,6 +1269,13 @@ ORed together. The letters are seen in "Tainted" line of Oops reports.
 
 See :doc:`/admin-guide/tainted-kernels` for more information.
 
+Note:
+  writes to this sysctl interface will fail with ``EINVAL`` if the kernel is
+  booted with the command line option ``panic_on_taint=<bitmask>,nousertaint``
+  and any of the ORed together values being written to ``tainted`` match with
+  the bitmask declared on panic_on_taint.
+  See :doc:`/admin-guide/kernel-parameters` for more details on that particular
+  kernel command line option and its optional ``nousertaint`` switch.
 
 threads-max
 ===========

Documentation/core-api/pin_user_pages.rst

@@ -148,23 +148,46 @@ NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's
 because DAX pages do not have a separate page cache, and so "pinning" implies
 locking down file system blocks, which is not (yet) supported in that way.
 
-CASE 3: Hardware with page faulting support
+CASE 3: MMU notifier registration, with or without page faulting hardware
--------------------------------------------
+-------------------------------------------------------------------------
-Here, a well-written driver doesn't normally need to pin pages at all. However,
+Device drivers can pin pages via get_user_pages*(), and register for mmu
-if the driver does choose to do so, it can register MMU notifiers for the range,
+notifier callbacks for the memory range. Then, upon receiving a notifier
-and will be called back upon invalidation. Either way (avoiding page pinning, or
+"invalidate range" callback , stop the device from using the range, and unpin
-using MMU notifiers to unpin upon request), there is proper synchronization with
+the pages. There may be other possible schemes, such as for example explicitly
-both filesystem and mm (page_mkclean(), munmap(), etc).
+synchronizing against pending IO, that accomplish approximately the same thing.
 
-Therefore, neither flag needs to be set.
+Or, if the hardware supports replayable page faults, then the device driver can
+avoid pinning entirely (this is ideal), as follows: register for mmu notifier
+callbacks as above, but instead of stopping the device and unpinning in the
+callback, simply remove the range from the device's page tables.
 
-In this case, ideally, neither get_user_pages() nor pin_user_pages() should be
+Either way, as long as the driver unpins the pages upon mmu notifier callback,
-called. Instead, the software should be written so that it does not pin pages.
+then there is proper synchronization with both filesystem and mm
-This allows mm and filesystems to operate more efficiently and reliably.
+(page_mkclean(), munmap(), etc). Therefore, neither flag needs to be set.
 
 CASE 4: Pinning for struct page manipulation only
 -------------------------------------------------
-Here, normal GUP calls are sufficient, so neither flag needs to be set.
+If only struct page data (as opposed to the actual memory contents that a page
+is tracking) is affected, then normal GUP calls are sufficient, and neither flag
+needs to be set.
+
+CASE 5: Pinning in order to write to the data within the page
+-------------------------------------------------------------
+Even though neither DMA nor Direct IO is involved, just a simple case of "pin,
+write to a page's data, unpin" can cause a problem. Case 5 may be considered a
+superset of Case 1, plus Case 2, plus anything that invokes that pattern. In
+other words, if the code is neither Case 1 nor Case 2, it may still require
+FOLL_PIN, for patterns like this:
+
+Correct (uses FOLL_PIN calls):
+    pin_user_pages()
+    write to the data within the pages
+    unpin_user_pages()
+
+INCORRECT (uses FOLL_GET calls):
+    get_user_pages()
+    write to the data within the pages
+    put_page()
 
 page_maybe_dma_pinned(): the whole point of pinning
 ===================================================

Documentation/dev-tools/kselftest.rst

@@ -151,6 +151,29 @@ note some tests will require root privileges::
    $ cd kselftest
    $ ./run_kselftest.sh
 
+Packaging selftests
+===================
+
+In some cases packaging is desired, such as when tests need to run on a
+different system. To package selftests, run::
+
+   $ make -C tools/testing/selftests gen_tar
+
+This generates a tarball in the `INSTALL_PATH/kselftest-packages` directory. By
+default, `.gz` format is used. The tar format can be overridden by specifying
+a `FORMAT` make variable. Any value recognized by `tar's auto-compress`_ option
+is supported, such as::
+
+    $ make -C tools/testing/selftests gen_tar FORMAT=.xz
+
+`make gen_tar` invokes `make install` so you can use it to package a subset of
+tests by using variables specified in `Running a subset of selftests`_
+section::
+
+    $ make -C tools/testing/selftests gen_tar TARGETS="bpf" FORMAT=.xz
+
+.. _tar's auto-compress: https://www.gnu.org/software/tar/manual/html_node/gzip.html#auto_002dcompress
+
 Contributing new tests
 ======================
 

Documentation/dev-tools/kunit/start.rst

@@ -32,15 +32,17 @@ test targets as well. The ``.kunitconfig`` should also contain any other config
 options required by the tests.
 
 A good starting point for a ``.kunitconfig`` is the KUnit defconfig:
+
 .. code-block:: bash
 
 	cd $PATH_TO_LINUX_REPO
 	cp arch/um/configs/kunit_defconfig .kunitconfig
 
 You can then add any other Kconfig options you wish, e.g.:
+
 .. code-block:: none
 
-        CONFIG_LIST_KUNIT_TEST=y
+	CONFIG_LIST_KUNIT_TEST=y
 
 :doc:`kunit_tool <kunit-tool>` will ensure that all config options set in
 ``.kunitconfig`` are set in the kernel ``.config`` before running the tests.
@@ -54,8 +56,8 @@ using.
    other tools (such as make menuconfig) to adjust other config options.
 
 
-Running the tests
+Running the tests (KUnit Wrapper)
------------------
+---------------------------------
 
 To make sure that everything is set up correctly, simply invoke the Python
 wrapper from your kernel repo:
@@ -105,8 +107,9 @@ have config options ending in ``_KUNIT_TEST``.
 KUnit and KUnit tests can be compiled as modules: in this case the tests in a
 module will be run when the module is loaded.
 
-Running the tests
+
------------------
+Running the tests (w/o KUnit Wrapper)
+-------------------------------------
 
 Build and run your kernel as usual. Test output will be written to the kernel
 log in `TAP <https://testanything.org/>`_ format.

Documentation/dev-tools/kunit/usage.rst

@@ -595,7 +595,7 @@ able to run one test case per invocation.
 KUnit debugfs representation
 ============================
 When kunit test suites are initialized, they create an associated directory
-in /sys/kernel/debug/kunit/<test-suite>.  The directory contains one file
+in ``/sys/kernel/debug/kunit/<test-suite>``.  The directory contains one file
 
 - results: "cat results" displays results of each test case and the results
   of the entire suite for the last test run.
@@ -604,4 +604,4 @@ The debugfs representation is primarily of use when kunit test suites are
 run in a native environment, either as modules or builtin.  Having a way
 to display results like this is valuable as otherwise results can be
 intermixed with other events in dmesg output.  The maximum size of each
-results file is KUNIT_LOG_SIZE bytes (defined in include/kunit/test.h).
+results file is KUNIT_LOG_SIZE bytes (defined in ``include/kunit/test.h``).

Documentation/devicetree/bindings/iommu/allwinner,sun50i-h6-iommu.yaml

@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/allwinner,sun50i-h6-iommu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner H6 IOMMU Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#iommu-cells":
+    const: 1
+    description:
+      The content of the cell is the master ID.
+
+  compatible:
+    const: allwinner,sun50i-h6-iommu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+required:
+  - "#iommu-cells"
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+      #include <dt-bindings/interrupt-controller/arm-gic.h>
+      #include <dt-bindings/interrupt-controller/irq.h>
+
+      #include <dt-bindings/clock/sun50i-h6-ccu.h>
+      #include <dt-bindings/reset/sun50i-h6-ccu.h>
+
+      iommu: iommu@30f0000 {
+          compatible = "allwinner,sun50i-h6-iommu";
+          reg = <0x030f0000 0x10000>;
+          interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+          clocks = <&ccu CLK_BUS_IOMMU>;
+          resets = <&ccu RST_BUS_IOMMU>;
+          #iommu-cells = <1>;
+      };
+
+...

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -42,7 +42,9 @@ properties:
           - const: arm,mmu-500
           - const: arm,smmu-v2
       - items:
-          - const: arm,mmu-401
+          - enum:
+              - arm,mmu-400
+              - arm,mmu-401
           - const: arm,smmu-v1
       - enum:
           - arm,smmu-v1

Documentation/devicetree/bindings/remoteproc/ingenic,vpu.yaml

@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/remoteproc/ingenic,vpu.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Ingenic Video Processing Unit bindings
+
+description:
+  Inside the Video Processing Unit (VPU) of the recent JZ47xx SoCs from
+  Ingenic is a second Xburst MIPS CPU very similar to the main core.
+  This document describes the devicetree bindings for this auxiliary
+  processor.
+
+maintainers:
+  - Paul Cercueil <paul@crapouillou.net>
+
+properties:
+  compatible:
+    const: ingenic,jz4770-vpu-rproc
+
+  reg:
+    items:
+      - description: aux registers
+      - description: tcsm0 registers
+      - description: tcsm1 registers
+      - description: sram registers
+
+  reg-names:
+    items:
+      - const: aux
+      - const: tcsm0
+      - const: tcsm1
+      - const: sram
+
+  clocks:
+    items:
+      - description: aux clock
+      - description: vpu clock
+
+  clock-names:
+    items:
+      - const: aux
+      - const: vpu
+
+  interrupts:
+    description: VPU hardware interrupt
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - clocks
+  - clock-names
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/jz4770-cgu.h>
+
+    vpu: video-decoder@132a0000 {
+      compatible = "ingenic,jz4770-vpu-rproc";
+
+      reg = <0x132a0000 0x20>, /* AUX */
+            <0x132b0000 0x4000>, /* TCSM0 */
+            <0x132c0000 0xc000>, /* TCSM1 */
+            <0x132f0000 0x7000>; /* SRAM */
+      reg-names = "aux", "tcsm0", "tcsm1", "sram";
+
+      clocks = <&cgu JZ4770_CLK_AUX>, <&cgu JZ4770_CLK_VPU>;
+      clock-names = "aux", "vpu";
+
+      interrupt-parent = <&cpuintc>;
+      interrupts = <3>;
+    };

Documentation/devicetree/bindings/remoteproc/qcom,adsp.txt

@@ -15,12 +15,16 @@ on the Qualcomm ADSP Hexagon core.
 		    "qcom,qcs404-adsp-pas"
 		    "qcom,qcs404-cdsp-pas"
 		    "qcom,qcs404-wcss-pas"
+		    "qcom,sc7180-mpss-pas"
 		    "qcom,sdm845-adsp-pas"
 		    "qcom,sdm845-cdsp-pas"
 		    "qcom,sm8150-adsp-pas"
 		    "qcom,sm8150-cdsp-pas"
 		    "qcom,sm8150-mpss-pas"
 		    "qcom,sm8150-slpi-pas"
+		    "qcom,sm8250-adsp-pas"
+		    "qcom,sm8250-cdsp-pas"
+		    "qcom,sm8250-slpi-pas"
 
 - interrupts-extended:
 	Usage: required
@@ -44,8 +48,12 @@ on the Qualcomm ADSP Hexagon core.
 	qcom,sm8150-adsp-pas:
 	qcom,sm8150-cdsp-pas:
 	qcom,sm8150-slpi-pas:
+	qcom,sm8250-adsp-pas:
+	qcom,sm8250-cdsp-pas:
+	qcom,sm8250-slpi-pas:
 		    must be "wdog", "fatal", "ready", "handover", "stop-ack"
 	qcom,qcs404-wcss-pas:
+	qcom,sc7180-mpss-pas:
 	qcom,sm8150-mpss-pas:
 		    must be "wdog", "fatal", "ready", "handover", "stop-ack",
 		    "shutdown-ack"
@@ -105,10 +113,14 @@ on the Qualcomm ADSP Hexagon core.
 	qcom,sdm845-cdsp-pas:
 	qcom,sm8150-adsp-pas:
 	qcom,sm8150-cdsp-pas:
+	qcom,sm8250-cdsp-pas:
 		    must be "cx", "load_state"
+	qcom,sc7180-mpss-pas:
 	qcom,sm8150-mpss-pas:
 		    must be "cx", "load_state", "mss"
+	qcom,sm8250-adsp-pas:
 	qcom,sm8150-slpi-pas:
+	qcom,sm8250-slpi-pas:
 		    must be "lcx", "lmx", "load_state"
 
 - memory-region:

Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt

@@ -79,7 +79,7 @@ on the Qualcomm Hexagon core.
 		    "snoc_axi", "mnoc_axi", "qdss"
 	qcom,sc7180-mss-pil:
 		    must be "iface", "bus", "xo", "snoc_axi", "mnoc_axi",
-		    "mss_crypto", "mss_nav", "nav"
+		    "nav"
 	qcom,sdm845-mss-pil:
 		    must be "iface", "bus", "mem", "xo", "gpll0_mss",
 		    "snoc_axi", "mnoc_axi", "prng"
@@ -102,6 +102,14 @@ on the Qualcomm Hexagon core.
 		    must be "mss_restart", "pdc_reset" for the modem
 		    sub-system on SC7180, SDM845 SoCs
 
+For devices where the mba and mpss sub-nodes are not specified, mba/mpss region
+should be referenced as follows:
+- memory-region:
+	Usage: required
+	Value type: <phandle>
+	Definition: reference to the reserved-memory for the mba region followed
+		    by the mpss region
+
 For the compatible strings below the following supplies are required:
   "qcom,q6v5-pil"
   "qcom,msm8916-mss-pil",
@@ -173,16 +181,15 @@ For the compatible string below the following supplies are required:
 
 For the compatible strings below the following phandle references are required:
   "qcom,sc7180-mss-pil"
-- qcom,halt-nav-regs:
+- qcom,spare-regs:
 	Usage: required
 	Value type: <prop-encoded-array>
-	Definition: reference to a list of 2 phandles with one offset each for
+	Definition: a phandle reference to a syscon representing TCSR followed
-		    the modem sub-system running on SC7180 SoC. The first
+		    by the offset within syscon for conn_box_spare0 register
-		    phandle reference is to the mss clock node followed by the
+		    used by the modem sub-system running on SC7180 SoC.
-		    offset within register space for nav halt register. The
+
-		    second phandle reference is to a syscon representing TCSR
+The Hexagon node must contain iommus property as described in ../iommu/iommu.txt
-		    followed by the offset within syscon for conn_box_spare0
+on platforms which do not have TrustZone.
-		    register.
 
 = SUBNODES:
 The Hexagon node must contain two subnodes, named "mba" and "mpss" representing

Documentation/filesystems/gfs2-glocks.rst

@@ -1,5 +1,8 @@
-                   Glock internal locking rules
+.. SPDX-License-Identifier: GPL-2.0
-                  ------------------------------
+
+============================
+Glock internal locking rules
+============================
 
 This documents the basic principles of the glock state machine
 internals. Each glock (struct gfs2_glock in fs/gfs2/incore.h)
@@ -24,24 +27,28 @@ There are three lock states that users of the glock layer can request,
 namely shared (SH), deferred (DF) and exclusive (EX). Those translate
 to the following DLM lock modes:
 
-Glock mode    | DLM lock mode
+==========	====== =====================================================
-------------------------------
+Glock mode      DLM    lock mode
-    UN        |    IV/NL  Unlocked (no DLM lock associated with glock) or NL
+==========	====== =====================================================
-    SH        |    PR     (Protected read)
+    UN          IV/NL  Unlocked (no DLM lock associated with glock) or NL
-    DF        |    CW     (Concurrent write)
+    SH          PR     (Protected read)
-    EX        |    EX     (Exclusive)
+    DF          CW     (Concurrent write)
+    EX          EX     (Exclusive)
+==========	====== =====================================================
 
 Thus DF is basically a shared mode which is incompatible with the "normal"
 shared lock mode, SH. In GFS2 the DF mode is used exclusively for direct I/O
 operations. The glocks are basically a lock plus some routines which deal
 with cache management. The following rules apply for the cache:
 
-Glock mode   |  Cache data | Cache Metadata | Dirty Data | Dirty Metadata
+==========      ==========   ==============   ==========   ==============
---------------------------------------------------------------------------
+Glock mode      Cache data   Cache Metadata   Dirty Data   Dirty Metadata
-    UN       |     No      |       No       |     No     |      No
+==========      ==========   ==============   ==========   ==============
-    SH       |     Yes     |       Yes      |     No     |      No
+    UN             No              No             No            No
-    DF       |     No      |       Yes      |     No     |      No
+    SH             Yes             Yes            No            No
-    EX       |     Yes     |       Yes      |     Yes    |      Yes
+    DF             No              Yes            No            No
+    EX             Yes             Yes            Yes           Yes
+==========      ==========   ==============   ==========   ==============
 
 These rules are implemented using the various glock operations which
 are defined for each type of glock. Not all types of glocks use
@@ -49,21 +56,23 @@ all the modes. Only inode glocks use the DF mode for example.
 
 Table of glock operations and per type constants:
 
-Field            | Purpose
+=============      =============================================================
-----------------------------------------------------------------------------
+Field              Purpose
-go_xmote_th      | Called before remote state change (e.g. to sync dirty data)
+=============      =============================================================
-go_xmote_bh      | Called after remote state change (e.g. to refill cache)
+go_xmote_th        Called before remote state change (e.g. to sync dirty data)
-go_inval         | Called if remote state change requires invalidating the cache
+go_xmote_bh        Called after remote state change (e.g. to refill cache)
-go_demote_ok     | Returns boolean value of whether its ok to demote a glock
+go_inval           Called if remote state change requires invalidating the cache
-                 | (e.g. checks timeout, and that there is no cached data)
+go_demote_ok       Returns boolean value of whether its ok to demote a glock
-go_lock          | Called for the first local holder of a lock
+                   (e.g. checks timeout, and that there is no cached data)
-go_unlock        | Called on the final local unlock of a lock
+go_lock            Called for the first local holder of a lock
-go_dump          | Called to print content of object for debugfs file, or on
+go_unlock          Called on the final local unlock of a lock
-                 | error to dump glock to the log.
+go_dump            Called to print content of object for debugfs file, or on
-go_type          | The type of the glock, LM_TYPE_.....
+                   error to dump glock to the log.
-go_callback	 | Called if the DLM sends a callback to drop this lock
+go_type            The type of the glock, ``LM_TYPE_*``
-go_flags	 | GLOF_ASPACE is set, if the glock has an address space
+go_callback	   Called if the DLM sends a callback to drop this lock
-                 | associated with it
+go_flags	   GLOF_ASPACE is set, if the glock has an address space
+                   associated with it
+=============      =============================================================
 
 The minimum hold time for each lock is the time after a remote lock
 grant for which we ignore remote demote requests. This is in order to
@@ -82,21 +91,25 @@ rather than via the glock.
 
 Locking rules for glock operations:
 
-Operation     |  GLF_LOCK bit lock held |  gl_lockref.lock spinlock held
+=============    ======================    =============================
--------------------------------------------------------------------------
+Operation        GLF_LOCK bit lock held    gl_lockref.lock spinlock held
-go_xmote_th   |       Yes               |       No
+=============    ======================    =============================
-go_xmote_bh   |       Yes               |       No
+go_xmote_th           Yes                       No
-go_inval      |       Yes               |       No
+go_xmote_bh           Yes                       No
-go_demote_ok  |       Sometimes         |       Yes
+go_inval              Yes                       No
-go_lock       |       Yes               |       No
+go_demote_ok          Sometimes                 Yes
-go_unlock     |       Yes               |       No
+go_lock               Yes                       No
-go_dump       |       Sometimes         |       Yes
+go_unlock             Yes                       No
-go_callback   |       Sometimes (N/A)   |       Yes
+go_dump               Sometimes                 Yes
+go_callback           Sometimes (N/A)           Yes
+=============    ======================    =============================
 
-N.B. Operations must not drop either the bit lock or the spinlock
+.. Note::
-if its held on entry. go_dump and do_demote_ok must never block.
+
-Note that go_dump will only be called if the glock's state
+   Operations must not drop either the bit lock or the spinlock
-indicates that it is caching uptodate data.
+   if its held on entry. go_dump and do_demote_ok must never block.
+   Note that go_dump will only be called if the glock's state
+   indicates that it is caching uptodate data.
 
 Glock locking order within GFS2:
 
@@ -104,7 +117,7 @@ Glock locking order within GFS2:
  2. Rename glock (for rename only)
  3. Inode glock(s)
     (Parents before children, inodes at "same level" with same parent in
-     lock number order)
+    lock number order)
  4. Rgrp glock(s) (for (de)allocation operations)
  5. Transaction glock (via gfs2_trans_begin) for non-read operations
  6. i_rw_mutex (if required)
@@ -117,8 +130,8 @@ determine the lifetime of the inode in question. Locking of inodes
 is on a per-inode basis. Locking of rgrps is on a per rgrp basis.
 In general we prefer to lock local locks prior to cluster locks.
 
-                            Glock Statistics
+Glock Statistics
-                           ------------------
+----------------
 
 The stats are divided into two sets: those relating to the
 super block and those relating to an individual glock. The
@@ -173,8 +186,8 @@ we'd like to get a better idea of these timings:
 1. To be able to better set the glock "min hold time"
 2. To spot performance issues more easily
 3. To improve the algorithm for selecting resource groups for
-allocation (to base it on lock wait time, rather than blindly
+   allocation (to base it on lock wait time, rather than blindly
-using a "try lock")
+   using a "try lock")
 
 Due to the smoothing action of the updates, a step change in
 some input quantity being sampled will only fully be taken
@@ -195,10 +208,13 @@ as possible. There are always inaccuracies in any
 measuring system, but I hope this is as accurate as we
 can reasonably make it.
 
-Per sb stats can be found here:
+Per sb stats can be found here::
-/sys/kernel/debug/gfs2/<fsname>/sbstats
+
-Per glock stats can be found here:
+    /sys/kernel/debug/gfs2/<fsname>/sbstats
-/sys/kernel/debug/gfs2/<fsname>/glstats
+
+Per glock stats can be found here::
+
+    /sys/kernel/debug/gfs2/<fsname>/glstats
 
 Assuming that debugfs is mounted on /sys/kernel/debug and also
 that <fsname> is replaced with the name of the gfs2 filesystem
@@ -206,14 +222,16 @@ in question.
 
 The abbreviations used in the output as are follows:
 
-srtt     - Smoothed round trip time for non-blocking dlm requests
+=========  ================================================================
-srttvar  - Variance estimate for srtt
+srtt       Smoothed round trip time for non blocking dlm requests
-srttb    - Smoothed round trip time for (potentially) blocking dlm requests
+srttvar    Variance estimate for srtt
-srttvarb - Variance estimate for srttb
+srttb      Smoothed round trip time for (potentially) blocking dlm requests
-sirt     - Smoothed inter-request time (for dlm requests)
+srttvarb   Variance estimate for srttb
-sirtvar  - Variance estimate for sirt
+sirt       Smoothed inter request time (for dlm requests)
-dlm      - Number of dlm requests made (dcnt in glstats file)
+sirtvar    Variance estimate for sirt
-queue    - Number of glock requests queued (qcnt in glstats file)
+dlm        Number of dlm requests made (dcnt in glstats file)
+queue      Number of glock requests queued (qcnt in glstats file)
+=========  ================================================================
 
 The sbstats file contains a set of these stats for each glock type (so 8 lines
 for each type) and for each cpu (one column per cpu). The glstats file contains
@@ -224,9 +242,12 @@ The gfs2_glock_lock_time tracepoint prints out the current values of the stats
 for the glock in question, along with some addition information on each dlm
 reply that is received:
 
-status - The status of the dlm request
+======   =======================================
-flags  - The dlm request flags
+status   The status of the dlm request
-tdiff  - The time taken by this specific request
+flags    The dlm request flags
+tdiff    The time taken by this specific request
+======   =======================================
+
 (remaining fields as per above list)
 
 

Documentation/filesystems/index.rst

@@ -88,6 +88,7 @@ Documentation for filesystem implementations.
    f2fs
    gfs2
    gfs2-uevents
+   gfs2-glocks
    hfs
    hfsplus
    hpfs

Documentation/filesystems/locking.rst

@@ -615,7 +615,7 @@ prototypes::
 locking rules:
 
 =============	========	===========================
-ops		mmap_sem	PageLocked(page)
+ops		mmap_lock	PageLocked(page)
 =============	========	===========================
 open:		yes
 close:		yes

Documentation/s390/index.rst

@@ -15,6 +15,7 @@ s390 Architecture
     vfio-ccw
     zfcpdump
     common_io
+    pci
 
     text_files
 

Documentation/s390/pci.rst

@@ -0,0 +1,125 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========
+S/390 PCI
+=========
+
+Authors:
+        - Pierre Morel
+
+Copyright, IBM Corp. 2020
+
+
+Command line parameters and debugfs entries
+===========================================
+
+Command line parameters
+-----------------------
+
+* nomio
+
+  Do not use PCI Mapped I/O (MIO) instructions.
+
+* norid
+
+  Ignore the RID field and force use of one PCI domain per PCI function.
+
+debugfs entries
+---------------
+
+The S/390 debug feature (s390dbf) generates views to hold various debug results in sysfs directories of the form:
+
+ * /sys/kernel/debug/s390dbf/pci_*/
+
+For example:
+
+  - /sys/kernel/debug/s390dbf/pci_msg/sprintf
+    Holds messages from the processing of PCI events, like machine check handling
+    and setting of global functionality, like UID checking.
+
+  Change the level of logging to be more or less verbose by piping
+  a number between 0 and 6 to  /sys/kernel/debug/s390dbf/pci_*/level. For
+  details, see the documentation on the S/390 debug feature at
+  Documentation/s390/s390dbf.rst.
+
+Sysfs entries
+=============
+
+Entries specific to zPCI functions and entries that hold zPCI information.
+
+* /sys/bus/pci/slots/XXXXXXXX
+
+  The slot entries are set up using the function identifier (FID) of the
+  PCI function.
+
+  - /sys/bus/pci/slots/XXXXXXXX/power
+
+  A physical function that currently supports a virtual function cannot be
+  powered off until all virtual functions are removed with:
+  echo 0 > /sys/bus/pci/devices/XXXX:XX:XX.X/sriov_numvf
+
+* /sys/bus/pci/devices/XXXX:XX:XX.X/
+
+  - function_id
+    A zPCI function identifier that uniquely identifies the function in the Z server.
+
+  - function_handle
+    Low-level identifier used for a configured PCI function.
+    It might be useful for debuging.
+
+  - pchid
+    Model-dependent location of the I/O adapter.
+
+  - pfgid
+    PCI function group ID, functions that share identical functionality
+    use a common identifier.
+    A PCI group defines interrupts, IOMMU, IOTLB, and DMA specifics.
+
+  - vfn
+    The virtual function number, from 1 to N for virtual functions,
+    0 for physical functions.
+
+  - pft
+    The PCI function type
+
+  - port
+    The port corresponds to the physical port the function is attached to.
+    It also gives an indication of the physical function a virtual function
+    is attached to.
+
+  - uid
+    The unique identifier (UID) is defined when configuring an LPAR and is
+    unique in the LPAR.
+
+  - pfip/segmentX
+    The segments determine the isolation of a function.
+    They correspond to the physical path to the function.
+    The more the segments are different, the more the functions are isolated.
+
+Enumeration and hotplug
+=======================
+
+The PCI address consists of four parts: domain, bus, device and function,
+and is of this form: DDDD:BB:dd.f
+
+* When not using multi-functions (norid is set, or the firmware does not
+  support multi-functions):
+
+  - There is only one function per domain.
+
+  - The domain is set from the zPCI function's UID as defined during the
+    LPAR creation.
+
+* When using multi-functions (norid parameter is not set),
+  zPCI functions are addressed differently:
+
+  - There is still only one bus per domain.
+
+  - There can be up to 256 functions per bus.
+
+  - The domain part of the address of all functions for
+    a multi-Function device is set from the zPCI function's UID as defined
+    in the LPAR creation for the function zero.
+
+  - New functions will only be ready for use after the function zero
+    (the function with devfn 0) has been enumerated.

Documentation/s390/vfio-ccw.rst

@@ -204,15 +204,44 @@ definition of the region is::
 	  __u32   ret_code;
   } __packed;
 
+This region is always available.
+
 While starting an I/O request, orb_area should be filled with the
 guest ORB, and scsw_area should be filled with the SCSW of the Virtual
 Subchannel.
 
 irb_area stores the I/O result.
 
-ret_code stores a return code for each access of the region.
+ret_code stores a return code for each access of the region. The following
+values may occur:
+
+``0``
+  The operation was successful.
+
+``-EOPNOTSUPP``
+  The orb specified transport mode or an unidentified IDAW format, or the
+  scsw specified a function other than the start function.
+
+``-EIO``
+  A request was issued while the device was not in a state ready to accept
+  requests, or an internal error occurred.
+
+``-EBUSY``
+  The subchannel was status pending or busy, or a request is already active.
+
+``-EAGAIN``
+  A request was being processed, and the caller should retry.
+
+``-EACCES``
+  The channel path(s) used for the I/O were found to be not operational.
+
+``-ENODEV``
+  The device was found to be not operational.
+
+``-EINVAL``
+  The orb specified a chain longer than 255 ccws, or an internal error
+  occurred.
 
-This region is always available.
 
 vfio-ccw cmd region
 -------------------
@@ -231,6 +260,64 @@ This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD.
 
 Currently, CLEAR SUBCHANNEL and HALT SUBCHANNEL use this region.
 
+command specifies the command to be issued; ret_code stores a return code
+for each access of the region. The following values may occur:
+
+``0``
+  The operation was successful.
+
+``-ENODEV``
+  The device was found to be not operational.
+
+``-EINVAL``
+  A command other than halt or clear was specified.
+
+``-EIO``
+  A request was issued while the device was not in a state ready to accept
+  requests.
+
+``-EAGAIN``
+  A request was being processed, and the caller should retry.
+
+``-EBUSY``
+  The subchannel was status pending or busy while processing a halt request.
+
+vfio-ccw schib region
+---------------------
+
+The vfio-ccw schib region is used to return Subchannel-Information
+Block (SCHIB) data to userspace::
+
+  struct ccw_schib_region {
+  #define SCHIB_AREA_SIZE 52
+         __u8 schib_area[SCHIB_AREA_SIZE];
+  } __packed;
+
+This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_SCHIB.
+
+Reading this region triggers a STORE SUBCHANNEL to be issued to the
+associated hardware.
+
+vfio-ccw crw region
+---------------------
+
+The vfio-ccw crw region is used to return Channel Report Word (CRW)
+data to userspace::
+
+  struct ccw_crw_region {
+         __u32 crw;
+         __u32 pad;
+  } __packed;
+
+This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_CRW.
+
+Reading this region returns a CRW if one that is relevant for this
+subchannel (e.g. one reporting changes in channel path state) is
+pending, or all zeroes if not. If multiple CRWs are pending (including
+possibly chained CRWs), reading this region again will return the next
+one, until no more CRWs are pending and zeroes are returned. This is
+similar to how STORE CHANNEL REPORT WORD works.
+
 vfio-ccw operation details
 --------------------------
 
@@ -333,7 +420,14 @@ through DASD/ECKD device online in a guest now and use it as a block
 device.
 
 The current code allows the guest to start channel programs via
-START SUBCHANNEL, and to issue HALT SUBCHANNEL and CLEAR SUBCHANNEL.
+START SUBCHANNEL, and to issue HALT SUBCHANNEL, CLEAR SUBCHANNEL,
+and STORE SUBCHANNEL.
+
+Currently all channel programs are prefetched, regardless of the
+p-bit setting in the ORB.  As a result, self modifying channel
+programs are not supported.  For this reason, IPL has to be handled as
+a special case by a userspace/guest program; this has been implemented
+in QEMU's s390-ccw bios as of QEMU 4.1.
 
 vfio-ccw supports classic (command mode) channel I/O only. Transport
 mode (HPF) is not supported.

Documentation/s390/zfcpdump.rst

@@ -46,5 +46,5 @@ initramfs with a user space application that writes the dump to a SCSI
 partition.
 
 For more information on how to use zfcpdump refer to the s390 'Using the Dump
-Tools book', which is available from
+Tools' book, which is available from IBM Knowledge Center:
-http://www.ibm.com/developerworks/linux/linux390.
+https://www.ibm.com/support/knowledgecenter/linuxonibm/liaaf/lnz_r_dt.html

Documentation/vm/hmm.rst

@@ -191,15 +191,15 @@ The usage pattern is::
 
  again:
       range.notifier_seq = mmu_interval_read_begin(&interval_sub);
-      down_read(&mm->mmap_sem);
+      mmap_read_lock(mm);
       ret = hmm_range_fault(&range);
       if (ret) {
-          up_read(&mm->mmap_sem);
+          mmap_read_unlock(mm);
           if (ret == -EBUSY)
                  goto again;
           return ret;
       }
-      up_read(&mm->mmap_sem);
+      mmap_read_unlock(mm);
 
       take_lock(driver->update);
       if (mmu_interval_read_retry(&ni, range.notifier_seq) {

Documentation/vm/transhuge.rst

@@ -98,9 +98,9 @@ split_huge_page() or split_huge_pmd() has a cost.
 
 To make pagetable walks huge pmd aware, all you need to do is to call
 pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the
-mmap_sem in read (or write) mode to be sure a huge pmd cannot be
+mmap_lock in read (or write) mode to be sure a huge pmd cannot be
 created from under you by khugepaged (khugepaged collapse_huge_page
-takes the mmap_sem in write mode in addition to the anon_vma lock). If
+takes the mmap_lock in write mode in addition to the anon_vma lock). If
 pmd_trans_huge returns false, you just fallback in the old code
 paths. If instead pmd_trans_huge returns true, you have to take the
 page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the

MAINTAINERS

@@ -7251,7 +7251,7 @@ L:	cluster-devel@redhat.com
 S:	Supported
 W:	http://sources.redhat.com/cluster/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2.git
-F:	Documentation/filesystems/gfs2*.txt
+F:	Documentation/filesystems/gfs2*
 F:	fs/gfs2/
 F:	include/uapi/linux/gfs2_ondisk.h
 
@@ -8502,6 +8502,7 @@ F:	drivers/mtd/nand/raw/ingenic/
 F:	drivers/pinctrl/pinctrl-ingenic.c
 F:	drivers/power/supply/ingenic-battery.c
 F:	drivers/pwm/pwm-jz4740.c
+F:	drivers/remoteproc/ingenic_rproc.c
 F:	drivers/rtc/rtc-jz4740.c
 F:	drivers/tty/serial/8250/8250_ingenic.c
 F:	drivers/usb/musb/jz4740.c
@@ -14840,6 +14841,7 @@ S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	arch/s390/pci/
 F:	drivers/pci/hotplug/s390_pci_hpc.c
+F:	Documentation/s390/pci.rst
 
 S390 VFIO AP DRIVER
 M:	Tony Krowiak <akrowiak@linux.ibm.com>

arch/alpha/boot/bootp.c

@@ -16,7 +16,6 @@
 
 #include <asm/console.h>
 #include <asm/hwrpb.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 
 #include <stdarg.h>

arch/alpha/boot/bootpz.c

@@ -18,7 +18,6 @@
 
 #include <asm/console.h>
 #include <asm/hwrpb.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 
 #include <stdarg.h>

arch/alpha/boot/main.c

@@ -14,7 +14,6 @@
 
 #include <asm/console.h>
 #include <asm/hwrpb.h>
-#include <asm/pgtable.h>
 
 #include <stdarg.h>
 

arch/alpha/include/asm/cacheflush.h

@@ -4,19 +4,6 @@
 
 #include <linux/mm.h>
 
-/* Caches aren't brain-dead on the Alpha. */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
 /* Note that the following two definitions are _highly_ dependent
    on the contexts in which they are used in the kernel.  I personally
    think it is criminal how loosely defined these macros are.  */
@@ -48,7 +35,7 @@ extern void smp_imb(void);
 
 extern void __load_new_mm_context(struct mm_struct *);
 static inline void
-flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			unsigned long addr, int len)
 {
 	if (vma->vm_flags & VM_EXEC) {
@@ -59,20 +46,17 @@ flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 			mm->context[smp_processor_id()] = 0;
 	}
 }
-#else
+#define flush_icache_user_page flush_icache_user_page
-extern void flush_icache_user_range(struct vm_area_struct *vma,
+#else /* CONFIG_SMP */
+extern void flush_icache_user_page(struct vm_area_struct *vma,
 		struct page *page, unsigned long addr, int len);
-#endif
+#define flush_icache_user_page flush_icache_user_page
+#endif /* CONFIG_SMP */
 
 /* This is used only in __do_fault and do_swap_page.  */
 #define flush_icache_page(vma, page) \
-  flush_icache_user_range((vma), (page), 0, 0)
+	flush_icache_user_page((vma), (page), 0, 0)
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+#include <asm-generic/cacheflush.h>
-do { memcpy(dst, src, len); \
-     flush_icache_user_range(vma, page, vaddr, len); \
-} while (0)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
 
 #endif /* _ALPHA_CACHEFLUSH_H */

arch/alpha/include/asm/io.h

@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <asm/compiler.h>
-#include <asm/pgtable.h>
 #include <asm/machvec.h>
 #include <asm/hwrpb.h>
 

arch/alpha/include/asm/pgtable.h

@@ -276,15 +276,6 @@ extern inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) &= ~_PAGE_FOW; return
 extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; return pte; }
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
 
-#define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
-
-/* to find an entry in a page-table-directory. */
-#define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
-#define pgd_offset(mm, address)	((mm)->pgd+pgd_index(address))
-
 /*
  * The smp_read_barrier_depends() in the following functions are required to
  * order the load of *dir (the pointer in the top level page table) with any
@@ -305,6 +296,7 @@ extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
 	smp_read_barrier_depends(); /* see above */
 	return ret;
 }
+#define pmd_offset pmd_offset
 
 /* Find an entry in the third-level page table.. */
 extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
@@ -314,9 +306,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
 	smp_read_barrier_depends(); /* see above */
 	return ret;
 }
-
+#define pte_offset_kernel pte_offset_kernel
-#define pte_offset_map(dir,addr)	pte_offset_kernel((dir),(addr))
-#define pte_unmap(pte)			do { } while (0)
 
 extern pgd_t swapper_pg_dir[1024];
 
@@ -355,8 +345,6 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 
 extern void paging_init(void);
 
-#include <asm-generic/pgtable.h>
-
 /* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT.  */
 #define HAVE_ARCH_UNMAPPED_AREA
 

arch/alpha/kernel/process.c

@@ -37,7 +37,6 @@
 #include <asm/reg.h>
 #include <linux/uaccess.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/hwrpb.h>
 #include <asm/fpu.h>
 

arch/alpha/kernel/proto.h

@@ -2,8 +2,6 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 
-#include <asm/pgtable.h>
-
 /* Prototypes of functions used across modules here in this directory.  */
 
 #define vucp	volatile unsigned char  *

arch/alpha/kernel/ptrace.c

@@ -19,7 +19,6 @@
 #include <linux/audit.h>
 
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/fpu.h>
 
 #include "proto.h"

arch/alpha/kernel/setup.c

@@ -55,7 +55,6 @@ static struct notifier_block alpha_panic_block = {
 };
 
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/hwrpb.h>
 #include <asm/dma.h>
 #include <asm/mmu_context.h>

arch/alpha/kernel/smp.c

@@ -36,7 +36,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -740,7 +739,7 @@ ipi_flush_icache_page(void *x)
 }
 
 void
-flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			unsigned long addr, int len)
 {
 	struct mm_struct *mm = vma->vm_mm;

arch/alpha/kernel/sys_alcor.c

@@ -23,7 +23,6 @@
 #include <asm/dma.h>
 #include <asm/mmu_context.h>
 #include <asm/irq.h>
-#include <asm/pgtable.h>
 #include <asm/core_cia.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_cabriolet.c

@@ -23,7 +23,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_apecs.h>
 #include <asm/core_cia.h>
 #include <asm/core_lca.h>

arch/alpha/kernel/sys_dp264.c

@@ -26,7 +26,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_tsunami.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_eb64p.c

@@ -22,7 +22,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_apecs.h>
 #include <asm/core_lca.h>
 #include <asm/hwrpb.h>

arch/alpha/kernel/sys_eiger.c

@@ -23,7 +23,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_tsunami.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_jensen.c

@@ -25,7 +25,6 @@
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
 #include "proto.h"

arch/alpha/kernel/sys_marvel.c

@@ -18,7 +18,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_marvel.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_miata.c

@@ -22,7 +22,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_cia.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_mikasa.c

@@ -23,7 +23,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_apecs.h>
 #include <asm/core_cia.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_nautilus.c

@@ -40,7 +40,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_irongate.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_noritake.c

@@ -24,7 +24,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_apecs.h>
 #include <asm/core_cia.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_rawhide.c

@@ -21,7 +21,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_mcpcia.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_ruffian.c

@@ -23,7 +23,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_cia.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_rx164.c

@@ -22,7 +22,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_polaris.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_sable.c

@@ -21,7 +21,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_t2.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_sio.c

@@ -25,7 +25,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_apecs.h>
 #include <asm/core_lca.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_sx164.c

@@ -22,7 +22,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_cia.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_takara.c

@@ -21,7 +21,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_cia.h>
 #include <asm/tlbflush.h>
 

arch/alpha/kernel/sys_titan.c

@@ -26,7 +26,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_titan.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/sys_wildfire.c

@@ -20,7 +20,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/core_wildfire.h>
 #include <asm/hwrpb.h>
 #include <asm/tlbflush.h>

arch/alpha/kernel/traps.c

@@ -121,10 +121,10 @@ dik_show_code(unsigned int *pc)
 }
 
 static void
-dik_show_trace(unsigned long *sp)
+dik_show_trace(unsigned long *sp, const char *loglvl)
 {
 	long i = 0;
-	printk("Trace:\n");
+	printk("%sTrace:\n", loglvl);
 	while (0x1ff8 & (unsigned long) sp) {
 		extern char _stext[], _etext[];
 		unsigned long tmp = *sp;
@@ -133,24 +133,24 @@ dik_show_trace(unsigned long *sp)
 			continue;
 		if (tmp >= (unsigned long) &_etext)
 			continue;
-		printk("[<%lx>] %pSR\n", tmp, (void *)tmp);
+		printk("%s[<%lx>] %pSR\n", loglvl, tmp, (void *)tmp);
 		if (i > 40) {
-			printk(" ...");
+			printk("%s ...", loglvl);
 			break;
 		}
 	}
-	printk("\n");
+	printk("%s\n", loglvl);
 }
 
 static int kstack_depth_to_print = 24;
 
-void show_stack(struct task_struct *task, unsigned long *sp)
+void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
 {
 	unsigned long *stack;
 	int i;
 
 	/*
-	 * debugging aid: "show_stack(NULL);" prints the
+	 * debugging aid: "show_stack(NULL, NULL, KERN_EMERG);" prints the
 	 * back trace for this cpu.
 	 */
 	if(sp==NULL)
@@ -163,14 +163,14 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 		if ((i % 4) == 0) {
 			if (i)
 				pr_cont("\n");
-			printk("       ");
+			printk("%s       ", loglvl);
 		} else {
 			pr_cont(" ");
 		}
 		pr_cont("%016lx", *stack++);
 	}
 	pr_cont("\n");
-	dik_show_trace(sp);
+	dik_show_trace(sp, loglvl);
 }
 
 void
@@ -184,7 +184,7 @@ die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15)
 	printk("%s(%d): %s %ld\n", current->comm, task_pid_nr(current), str, err);
 	dik_show_regs(regs, r9_15);
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
-	dik_show_trace((unsigned long *)(regs+1));
+	dik_show_trace((unsigned long *)(regs+1), KERN_DEFAULT);
 	dik_show_code((unsigned int *)regs->pc);
 
 	if (test_and_set_thread_flag (TIF_DIE_IF_KERNEL)) {
@@ -625,7 +625,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 	printk("gp = %016lx  sp = %p\n", regs->gp, regs+1);
 
 	dik_show_code((unsigned int *)pc);
-	dik_show_trace((unsigned long *)(regs+1));
+	dik_show_trace((unsigned long *)(regs+1), KERN_DEFAULT);
 
 	if (test_and_set_thread_flag (TIF_DIE_IF_KERNEL)) {
 		printk("die_if_kernel recursion detected.\n");
@@ -957,12 +957,12 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 		si_code = SEGV_ACCERR;
 	else {
 		struct mm_struct *mm = current->mm;
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		if (find_vma(mm, (unsigned long)va))
 			si_code = SEGV_ACCERR;
 		else
 			si_code = SEGV_MAPERR;
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 	}
 	send_sig_fault(SIGSEGV, si_code, va, 0, current);
 	return;

arch/alpha/mm/fault.c

@@ -117,7 +117,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 retry:
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
 	if (!vma)
 		goto bad_area;
@@ -171,7 +171,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		if (fault & VM_FAULT_RETRY) {
 			flags |= FAULT_FLAG_TRIED;
 
-			 /* No need to up_read(&mm->mmap_sem) as we would
+			 /* No need to mmap_read_unlock(mm) as we would
 			 * have already released it in __lock_page_or_retry
 			 * in mm/filemap.c.
 			 */
@@ -180,14 +180,14 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		}
 	}
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return;
 
 	/* Something tried to access memory that isn't in our memory map.
 	   Fix it, but check if it's kernel or user first.  */
  bad_area:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	if (user_mode(regs))
 		goto do_sigsegv;
@@ -211,14 +211,14 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* We ran out of memory, or some other thing happened to us that
 	   made us unable to handle the page fault gracefully.  */
  out_of_memory:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();
 	return;
 
  do_sigbus:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	/* Send a sigbus, regardless of whether we were in kernel
 	   or user mode.  */
 	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address, 0);

arch/alpha/mm/init.c

@@ -24,7 +24,6 @@
 #include <linux/gfp.h>
 
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/hwrpb.h>
 #include <asm/dma.h>

arch/arc/include/asm/bug.h

@@ -13,7 +13,8 @@
 struct task_struct;
 
 void show_regs(struct pt_regs *regs);
-void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs);
+void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs,
+		     const char *loglvl);
 void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
 			    unsigned long address);
 void die(const char *str, struct pt_regs *regs, unsigned long address);

arch/arc/include/asm/pgtable.h

@@ -248,9 +248,6 @@
 extern char empty_zero_page[PAGE_SIZE];
 #define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
 
-#define pte_unmap(pte)		do { } while (0)
-#define pte_unmap_nested(pte)		do { } while (0)
-
 #define set_pte(pteptr, pteval)	((*(pteptr)) = (pteval))
 #define set_pmd(pmdptr, pmdval)	(*(pmdptr) = pmdval)
 
@@ -282,18 +279,6 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 
 /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
-#define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-
-/*
- * pte_offset gets a @ptr to PMD entry (PGD in our 2-tier paging system)
- * and returns ptr to PTE entry corresponding to @addr
- */
-#define pte_offset(dir, addr) ((pte_t *)(pmd_page_vaddr(*dir)) +\
-					 __pte_index(addr))
-
-/* No mapping of Page Tables in high mem etc, so following same as above */
-#define pte_offset_kernel(dir, addr)		pte_offset(dir, addr)
-#define pte_offset_map(dir, addr)		pte_offset(dir, addr)
 
 /* Zoo of pte_xxx function */
 #define pte_read(pte)		(pte_val(pte) & _PAGE_READ)
@@ -331,13 +316,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, pteval);
 }
 
-/*
- * All kernel related VM pages are in init's mm.
- */
-#define pgd_offset_k(address)	pgd_offset(&init_mm, address)
-#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
-#define pgd_offset(mm, addr)	(((mm)->pgd)+pgd_index(addr))
-
 /*
  * Macro to quickly access the PGD entry, utlising the fact that some
  * arch may cache the pointer to Page Directory of "current" task
@@ -390,8 +368,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 #include <asm/hugepage.h>
 #endif
 
-#include <asm-generic/pgtable.h>
-
 /* to cope with aliasing VIPT cache */
 #define HAVE_ARCH_UNMAPPED_AREA
 

arch/arc/kernel/process.c

@@ -90,10 +90,10 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 	if (unlikely(ret != -EFAULT))
 		 goto fail;
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
 			       FAULT_FLAG_WRITE, NULL);
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	if (likely(!ret))
 		 goto again;

arch/arc/kernel/stacktrace.c

@@ -158,9 +158,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 /* Call-back which plugs into unwinding core to dump the stack in
  * case of panic/OOPs/BUG etc
  */
-static int __print_sym(unsigned int address, void *unused)
+static int __print_sym(unsigned int address, void *arg)
 {
-	printk("  %pS\n", (void *)address);
+	const char *loglvl = arg;
+
+	printk("%s  %pS\n", loglvl, (void *)address);
 	return 0;
 }
 
@@ -217,17 +219,18 @@ static int __get_first_nonsched(unsigned int address, void *unused)
  *-------------------------------------------------------------------------
  */
 
-noinline void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs)
+noinline void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs,
+			      const char *loglvl)
 {
-	pr_info("\nStack Trace:\n");
+	printk("%s\nStack Trace:\n", loglvl);
-	arc_unwind_core(tsk, regs, __print_sym, NULL);
+	arc_unwind_core(tsk, regs, __print_sym, (void *)loglvl);
 }
 EXPORT_SYMBOL(show_stacktrace);
 
 /* Expected by sched Code */
-void show_stack(struct task_struct *tsk, unsigned long *sp)
+void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 {
-	show_stacktrace(tsk, NULL);
+	show_stacktrace(tsk, NULL, loglvl);
 }
 
 /* Another API expected by schedular, shows up in "ps" as Wait Channel

arch/arc/kernel/troubleshoot.c

@@ -89,7 +89,7 @@ static void show_faulting_vma(unsigned long address)
 	/* can't use print_vma_addr() yet as it doesn't check for
 	 * non-inclusive vma
 	 */
-	down_read(&active_mm->mmap_sem);
+	mmap_read_lock(active_mm);
 	vma = find_vma(active_mm, address);
 
 	/* check against the find_vma( ) behaviour which returns the next VMA
@@ -111,7 +111,7 @@ static void show_faulting_vma(unsigned long address)
 	} else
 		pr_info("    @No matching VMA found\n");
 
-	up_read(&active_mm->mmap_sem);
+	mmap_read_unlock(active_mm);
 }
 
 static void show_ecr_verbose(struct pt_regs *regs)
@@ -240,5 +240,5 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
 
 	/* Show stack trace if this Fatality happened in kernel mode */
 	if (!user_mode(regs))
-		show_stacktrace(current, regs);
+		show_stacktrace(current, regs, KERN_DEFAULT);
 }

arch/arc/mm/fault.c

@@ -107,7 +107,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 		flags |= FAULT_FLAG_WRITE;
 
 retry:
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -141,7 +141,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	}
 
 	/*
-	 * Fault retry nuances, mmap_sem already relinquished by core mm
+	 * Fault retry nuances, mmap_lock already relinquished by core mm
 	 */
 	if (unlikely((fault & VM_FAULT_RETRY) &&
 		     (flags & FAULT_FLAG_ALLOW_RETRY))) {
@@ -150,7 +150,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	}
 
 bad_area:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	/*
 	 * Major/minor page fault accounting

arch/arc/mm/highmem.c

@@ -6,8 +6,8 @@
 #include <linux/memblock.h>
 #include <linux/export.h>
 #include <linux/highmem.h>
+#include <linux/pgtable.h>
 #include <asm/processor.h>
-#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
@@ -92,17 +92,9 @@ EXPORT_SYMBOL(kunmap_atomic_high);
 
 static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
-	pgd_t *pgd_k;
+	pmd_t *pmd_k = pmd_off_k(kvaddr);
-	p4d_t *p4d_k;
-	pud_t *pud_k;
-	pmd_t *pmd_k;
 	pte_t *pte_k;
 
-	pgd_k = pgd_offset_k(kvaddr);
-	p4d_k = p4d_offset(pgd_k, kvaddr);
-	pud_k = pud_offset(p4d_k, kvaddr);
-	pmd_k = pmd_offset(pud_k, kvaddr);
-
 	pte_k = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
 	if (!pte_k)
 		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",

arch/arc/mm/tlbex.S

@@ -33,9 +33,9 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/pgtable.h>
 #include <asm/entry.h>
 #include <asm/mmu.h>
-#include <asm/pgtable.h>
 #include <asm/arcregs.h>
 #include <asm/cache.h>
 #include <asm/processor.h>

arch/arm/include/asm/bug.h

@@ -82,7 +82,8 @@ void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
 				       struct pt_regs *),
 		     int sig, int code, const char *name);
 
-extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
+extern asmlinkage void c_backtrace(unsigned long fp, int pmode,
+				   const char *loglvl);
 
 struct mm_struct;
 void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr);

arch/arm/include/asm/cacheflush.h

@@ -258,11 +258,11 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
 #define flush_cache_dup_mm(mm) flush_cache_mm(mm)
 
 /*
- * flush_cache_user_range is used when we want to ensure that the
+ * flush_icache_user_range is used when we want to ensure that the
  * Harvard caches are synchronised for the user space address range.
  * This is used for the ARM private sys_cacheflush system call.
  */
-#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
+#define flush_icache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
 
 /*
  * Perform necessary cache operations to ensure that data previously
@@ -318,9 +318,6 @@ extern void flush_kernel_dcache_page(struct page *);
 #define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
 #define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
 
-#define flush_icache_user_range(vma,page,addr,len) \
-	flush_dcache_page(page)
-
 /*
  * We don't appear to need to do anything here.  In fact, if we did, we'd
  * duplicate cache flushing elsewhere performed by flush_dcache_page().

arch/arm/include/asm/efi.h

@@ -13,7 +13,6 @@
 #include <asm/highmem.h>
 #include <asm/mach/map.h>
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_EFI

arch/arm/include/asm/fixmap.h

@@ -6,8 +6,8 @@
 #define FIXADDR_END		0xfff00000UL
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
+#include <linux/pgtable.h>
 #include <asm/kmap_types.h>
-#include <asm/pgtable.h>
 
 enum fixed_addresses {
 	FIX_EARLYCON_MEM_BASE,

arch/arm/include/asm/idmap.h

@@ -3,7 +3,7 @@
 #define __ASM_IDMAP_H
 
 #include <linux/compiler.h>
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
 
 /* Tag a function as requiring to be executed via an identity mapping. */
 #define __idmap __section(.idmap.text) noinline notrace

arch/arm/include/asm/pgtable-2level.h

@@ -187,6 +187,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 {
 	return (pmd_t *)pud;
 }
+#define pmd_offset pmd_offset
 
 #define pmd_large(pmd)		(pmd_val(pmd) & 2)
 #define pmd_leaf(pmd)		(pmd_val(pmd) & 2)

arch/arm/include/asm/pgtable-3level.h

@@ -133,13 +133,6 @@ static inline pmd_t *pud_page_vaddr(pud_t pud)
 	return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
 }
 
-/* Find an entry in the second-level page table.. */
-#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
-{
-	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
-}
-
 #define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
 
 #define copy_pmd(pmdpd,pmdps)		\

arch/arm/include/asm/pgtable-nommu.h

@@ -22,7 +22,6 @@
 #define pgd_bad(pgd)		(0)
 #define pgd_clear(pgdp)
 #define kern_addr_valid(addr)	(1)
-#define	pmd_offset(a, b)	((void *)0)
 /* FIXME */
 /*
  * PMD_SHIFT determines the size of the area a second-level page table can map
@@ -73,8 +72,6 @@ extern unsigned int kobjsize(const void *objp);
 
 #define FIRST_USER_ADDRESS      0UL
 
-#include <asm-generic/pgtable.h>
-
 #else 
 
 /*

arch/arm/include/asm/pgtable.h

@@ -166,14 +166,6 @@ extern struct page *empty_zero_page;
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
-/* to find an entry in a page-table-directory */
-#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
-
-#define pgd_offset(mm, addr)	((mm)->pgd + pgd_index(addr))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
-
 #define pmd_none(pmd)		(!pmd_val(pmd))
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
@@ -183,21 +175,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-#ifndef CONFIG_HIGHPTE
-#define __pte_map(pmd)		pmd_page_vaddr(*(pmd))
-#define __pte_unmap(pte)	do { } while (0)
-#else
-#define __pte_map(pmd)		(pte_t *)kmap_atomic(pmd_page(*(pmd)))
-#define __pte_unmap(pte)	kunmap_atomic(pte)
-#endif
-
-#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-
-#define pte_offset_kernel(pmd,addr)	(pmd_page_vaddr(*(pmd)) + pte_index(addr))
-
-#define pte_offset_map(pmd,addr)	(__pte_map(pmd) + pte_index(addr))
-#define pte_unmap(pte)			__pte_unmap(pte)
-
 #define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
 #define pfn_pte(pfn,prot)	__pte(__pfn_to_phys(pfn) | pgprot_val(prot))
 
@@ -339,8 +316,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 /* FIXME: this is not correct */
 #define kern_addr_valid(addr)	(1)
 
-#include <asm-generic/pgtable.h>
-
 /*
  * We provide our own arch_get_unmapped_area to cope with VIPT caches.
  */

arch/arm/include/asm/traps.h

@@ -29,7 +29,8 @@ static inline int __in_irqentry_text(unsigned long ptr)
 }
 
 extern void __init early_trap_init(void *);
-extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
+extern void dump_backtrace_entry(unsigned long where, unsigned long from,
+				 unsigned long frame, const char *loglvl);
 extern void ptrace_break(struct pt_regs *regs);
 
 extern void *vectors_page;

arch/arm/include/asm/unwind.h

@@ -36,7 +36,8 @@ extern struct unwind_table *unwind_table_add(unsigned long start,
 					     unsigned long text_addr,
 					     unsigned long text_size);
 extern void unwind_table_del(struct unwind_table *tab);
-extern void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk);
+extern void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+			     const char *loglvl);
 
 #endif	/* !__ASSEMBLY__ */
 

arch/arm/kernel/fiq.c

@@ -98,8 +98,8 @@ void set_fiq_handler(void *start, unsigned int length)
 
 	memcpy(base + offset, start, length);
 	if (!cache_is_vipt_nonaliasing())
-		flush_icache_range((unsigned long)base + offset, offset +
+		flush_icache_range((unsigned long)base + offset,
-				   length);
+				   (unsigned long)base + offset + length);
 	flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
 }
 

arch/arm/kernel/head.S

@@ -10,6 +10,7 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 
 #include <asm/assembler.h>
 #include <asm/cp15.h>
@@ -18,7 +19,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
-#include <asm/pgtable.h>
 
 #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
 #include CONFIG_DEBUG_LL_INCLUDE

arch/arm/kernel/machine_kexec.c

@@ -10,7 +10,6 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/memblock.h>
-#include <asm/pgtable.h>
 #include <linux/of_fdt.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>

arch/arm/kernel/module.c

@@ -17,7 +17,6 @@
 #include <linux/string.h>
 #include <linux/gfp.h>
 
-#include <asm/pgtable.h>
 #include <asm/sections.h>
 #include <asm/smp_plat.h>
 #include <asm/unwind.h>

arch/arm/kernel/process.c

@@ -431,7 +431,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	npages = 1; /* for sigpage */
 	npages += vdso_total_pages;
 
-	if (down_write_killable(&mm->mmap_sem))
+	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 	hint = sigpage_addr(mm, npages);
 	addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0);
@@ -458,7 +458,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	arm_install_vdso(mm, addr + PAGE_SIZE);
 
  up_fail:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	return ret;
 }
 #endif

arch/arm/kernel/ptrace.c

@@ -25,7 +25,6 @@
 #include <linux/tracehook.h>
 #include <linux/unistd.h>
 
-#include <asm/pgtable.h>
 #include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS

arch/arm/kernel/smp.c

@@ -37,7 +37,6 @@
 #include <asm/idmap.h>
 #include <asm/topology.h>
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/procinfo.h>
 #include <asm/processor.h>

arch/arm/kernel/suspend.c

@@ -2,12 +2,12 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
+#include <linux/pgtable.h>
 
 #include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
 #include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>

arch/arm/kernel/swp_emulate.c

@@ -97,12 +97,12 @@ static void set_segfault(struct pt_regs *regs, unsigned long addr)
 {
 	int si_code;
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	if (find_vma(current->mm, addr) == NULL)
 		si_code = SEGV_MAPERR;
 	else
 		si_code = SEGV_ACCERR;
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	pr_debug("SWP{B} emulation: access caused memory abort!\n");
 	arm_notify_die("Illegal memory access", regs,

arch/arm/kernel/traps.c

@@ -62,21 +62,24 @@ __setup("user_debug=", user_debug_setup);
 
 static void dump_mem(const char *, const char *, unsigned long, unsigned long);
 
-void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
+void dump_backtrace_entry(unsigned long where, unsigned long from,
+			  unsigned long frame, const char *loglvl)
 {
 	unsigned long end = frame + 4 + sizeof(struct pt_regs);
 
 #ifdef CONFIG_KALLSYMS
-	printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
+	printk("%s[<%08lx>] (%ps) from [<%08lx>] (%pS)\n",
+		loglvl, where, (void *)where, from, (void *)from);
 #else
-	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
+	printk("%sFunction entered at [<%08lx>] from [<%08lx>]\n",
+		loglvl, where, from);
 #endif
 
 	if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE))
-		dump_mem("", "Exception stack", frame + 4, end);
+		dump_mem(loglvl, "Exception stack", frame + 4, end);
 }
 
-void dump_backtrace_stm(u32 *stack, u32 instruction)
+void dump_backtrace_stm(u32 *stack, u32 instruction, const char *loglvl)
 {
 	char str[80], *p;
 	unsigned int x;
@@ -88,12 +91,12 @@ void dump_backtrace_stm(u32 *stack, u32 instruction)
 			if (++x == 6) {
 				x = 0;
 				p = str;
-				printk("%s\n", str);
+				printk("%s%s\n", loglvl, str);
 			}
 		}
 	}
 	if (p != str)
-		printk("%s\n", str);
+		printk("%s%s\n", loglvl, str);
 }
 
 #ifndef CONFIG_ARM_UNWIND
@@ -201,17 +204,19 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_ARM_UNWIND
-static inline void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+static inline void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+				  const char *loglvl)
 {
-	unwind_backtrace(regs, tsk);
+	unwind_backtrace(regs, tsk, loglvl);
 }
 #else
-static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+			   const char *loglvl)
 {
 	unsigned int fp, mode;
 	int ok = 1;
 
-	printk("Backtrace: ");
+	printk("%sBacktrace: ", loglvl);
 
 	if (!tsk)
 		tsk = current;
@@ -238,13 +243,13 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	pr_cont("\n");
 
 	if (ok)
-		c_backtrace(fp, mode);
+		c_backtrace(fp, mode, loglvl);
 }
 #endif
 
-void show_stack(struct task_struct *tsk, unsigned long *sp)
+void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 {
-	dump_backtrace(NULL, tsk);
+	dump_backtrace(NULL, tsk, loglvl);
 	barrier();
 }
 
@@ -288,7 +293,7 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 	if (!user_mode(regs) || in_interrupt()) {
 		dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp,
 			 THREAD_SIZE + (unsigned long)task_stack_page(tsk));
-		dump_backtrace(regs, tsk);
+		dump_backtrace(regs, tsk, KERN_EMERG);
 		dump_instr(KERN_EMERG, regs);
 	}
 
@@ -566,7 +571,7 @@ __do_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
-		ret = flush_cache_user_range(start, start + chunk);
+		ret = flush_icache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
 
@@ -663,10 +668,10 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 	if (user_debug & UDBG_SYSCALL) {
 		pr_err("[%d] %s: arm syscall %d\n",
 		       task_pid_nr(current), current->comm, no);
-		dump_instr("", regs);
+		dump_instr(KERN_ERR, regs);
 		if (user_mode(regs)) {
 			__show_regs(regs);
-			c_backtrace(frame_pointer(regs), processor_mode(regs));
+			c_backtrace(frame_pointer(regs), processor_mode(regs), KERN_ERR);
 		}
 	}
 #endif

arch/arm/kernel/unwind.c

@@ -455,7 +455,8 @@ int unwind_frame(struct stackframe *frame)
 	return URC_OK;
 }
 
-void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+		      const char *loglvl)
 {
 	struct stackframe frame;
 
@@ -493,7 +494,7 @@ void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		urc = unwind_frame(&frame);
 		if (urc < 0)
 			break;
-		dump_backtrace_entry(where, frame.pc, frame.sp - 4);
+		dump_backtrace_entry(where, frame.pc, frame.sp - 4, loglvl);
 	}
 }
 

arch/arm/kernel/vdso.c

@@ -240,7 +240,7 @@ static int install_vvar(struct mm_struct *mm, unsigned long addr)
 	return PTR_ERR_OR_ZERO(vma);
 }
 
-/* assumes mmap_sem is write-locked */
+/* assumes mmap_lock is write-locked */
 void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
 {
 	struct vm_area_struct *vma;

arch/arm/kernel/vmlinux.lds.S

@@ -8,13 +8,13 @@
 #include "vmlinux-xip.lds.S"
 #else
 
+#include <linux/pgtable.h>
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/mpu.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 
 #include "vmlinux.lds.h"
 

arch/arm/lib/backtrace-clang.S

@@ -17,6 +17,7 @@
 #define sv_pc	r6
 #define mask	r7
 #define sv_lr	r8
+#define loglvl	r9
 
 ENTRY(c_backtrace)
 
@@ -99,6 +100,7 @@ ENDPROC(c_backtrace)
 						@ to ensure 8 byte alignment
 		movs	frame, r0		@ if frame pointer is zero
 		beq	no_frame		@ we have no stack frames
+		mov	loglvl, r2
 		tst	r1, #0x10		@ 26 or 32-bit mode?
 		moveq	mask, #0xfc000003
 		movne	mask, #0		@ mask for 32-bit
@@ -167,6 +169,7 @@ finished_setup:
 		mov	r1, sv_lr
 		mov	r2, frame
 		bic	r1, r1, mask		@ mask PC/LR for the mode
+		mov	r3, loglvl
 		bl	dump_backtrace_entry
 
 /*
@@ -183,6 +186,7 @@ finished_setup:
 		ldr	r0, [frame]		@ locals are stored in
 						@ the preceding frame
 		subeq	r0, r0, #4
+		mov	r2, loglvl
 		bleq	dump_backtrace_stm	@ dump saved registers
 
 /*
@@ -196,7 +200,8 @@ finished_setup:
 		bhi	for_each_frame
 
 1006:		adr	r0, .Lbad
-		mov	r1, frame
+		mov	r1, loglvl
+		mov	r2, frame
 		bl	printk
 no_frame:	ldmfd	sp!, {r4 - r9, fp, pc}
 ENDPROC(c_backtrace)
@@ -209,7 +214,7 @@ ENDPROC(c_backtrace)
 		.long   1005b, 1006b
 		.popsection
 
-.Lbad:		.asciz	"Backtrace aborted due to bad frame pointer <%p>\n"
+.Lbad:		.asciz	"%sBacktrace aborted due to bad frame pointer <%p>\n"
 		.align
 .Lopcode:	.word	0xe92d4800 >> 11	@ stmfd sp!, {... fp, lr}
 		.word	0x0b000000		@ bl if these bits are set

arch/arm/lib/backtrace.S

@@ -18,6 +18,7 @@
 #define sv_pc	r6
 #define mask	r7
 #define offset	r8
+#define loglvl	r9
 
 ENTRY(c_backtrace)
 
@@ -25,9 +26,10 @@ ENTRY(c_backtrace)
 		ret	lr
 ENDPROC(c_backtrace)
 #else
-		stmfd	sp!, {r4 - r8, lr}	@ Save an extra register so we have a location...
+		stmfd	sp!, {r4 - r9, lr}	@ Save an extra register so we have a location...
 		movs	frame, r0		@ if frame pointer is zero
 		beq	no_frame		@ we have no stack frames
+		mov	loglvl, r2
 
 		tst	r1, #0x10		@ 26 or 32-bit mode?
  ARM(		moveq	mask, #0xfc000003	)
@@ -73,6 +75,7 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		ldr	r1, [frame, #-4]	@ get saved lr
 		mov	r2, frame
 		bic	r1, r1, mask		@ mask PC/LR for the mode
+		mov	r3, loglvl
 		bl	dump_backtrace_entry
 
 		ldr	r1, [sv_pc, #-4]	@ if stmfd sp!, {args} exists,
@@ -80,12 +83,14 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		teq	r3, r1, lsr #11
 		ldreq	r0, [frame, #-8]	@ get sp
 		subeq	r0, r0, #4		@ point at the last arg
+		mov	r2, loglvl
 		bleq	dump_backtrace_stm	@ dump saved registers
 
 1004:		ldr	r1, [sv_pc, #0]		@ if stmfd sp!, {..., fp, ip, lr, pc}
 		ldr	r3, .Ldsi		@ instruction exists,
 		teq	r3, r1, lsr #11
 		subeq	r0, frame, #16
+		mov	r2, loglvl
 		bleq	dump_backtrace_stm	@ dump saved registers
 
 		teq	sv_fp, #0		@ zero saved fp means
@@ -96,9 +101,10 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		bhi	for_each_frame
 
 1006:		adr	r0, .Lbad
-		mov	r1, frame
+		mov	r1, loglvl
+		mov	r2, frame
 		bl	printk
-no_frame:	ldmfd	sp!, {r4 - r8, pc}
+no_frame:	ldmfd	sp!, {r4 - r9, pc}
 ENDPROC(c_backtrace)
 		
 		.pushsection __ex_table,"a"
@@ -109,7 +115,7 @@ ENDPROC(c_backtrace)
 		.long	1004b, 1006b
 		.popsection
 
-.Lbad:		.asciz	"Backtrace aborted due to bad frame pointer <%p>\n"
+.Lbad:		.asciz	"%sBacktrace aborted due to bad frame pointer <%p>\n"
 		.align
 .Ldsi:		.word	0xe92dd800 >> 11	@ stmfd sp!, {... fp, ip, lr, pc}
 		.word	0xe92d0000 >> 11	@ stmfd sp!, {}

arch/arm/lib/uaccess_with_memcpy.c

@@ -101,7 +101,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 	atomic = faulthandler_disabled();
 
 	if (!atomic)
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(current->mm);
 	while (n) {
 		pte_t *pte;
 		spinlock_t *ptl;
@@ -109,11 +109,11 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 
 		while (!pin_page_for_write(to, &pte, &ptl)) {
 			if (!atomic)
-				up_read(&current->mm->mmap_sem);
+				mmap_read_unlock(current->mm);
 			if (__put_user(0, (char __user *)to))
 				goto out;
 			if (!atomic)
-				down_read(&current->mm->mmap_sem);
+				mmap_read_lock(current->mm);
 		}
 
 		tocopy = (~(unsigned long)to & ~PAGE_MASK) + 1;
@@ -133,7 +133,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 			spin_unlock(ptl);
 	}
 	if (!atomic)
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 
 out:
 	return n;
@@ -170,17 +170,17 @@ __clear_user_memset(void __user *addr, unsigned long n)
 		return 0;
 	}
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	while (n) {
 		pte_t *pte;
 		spinlock_t *ptl;
 		int tocopy;
 
 		while (!pin_page_for_write(addr, &pte, &ptl)) {
-			up_read(&current->mm->mmap_sem);
+			mmap_read_unlock(current->mm);
 			if (__put_user(0, (char __user *)addr))
 				goto out;
-			down_read(&current->mm->mmap_sem);
+			mmap_read_lock(current->mm);
 		}
 
 		tocopy = (~(unsigned long)addr & ~PAGE_MASK) + 1;
@@ -198,7 +198,7 @@ __clear_user_memset(void __user *addr, unsigned long n)
 		else
 			spin_unlock(ptl);
 	}
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 out:
 	return n;

arch/arm/mach-ebsa110/core.c

@@ -17,7 +17,6 @@
 #include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/system_misc.h>