ock: sync codes to ock 5.4.119-20.0009.21

Gitee limit the repo's size to 3GB, to reduce the size of the code,
sync codes to ock 5.4.119-20.0009.21 in one commit.

Signed-off-by: Jianping Liu <frankjpliu@tencent.com>

.gitattributes

@@ -1,2 +1,3 @@
 *.c   diff=cpp
 *.h   diff=cpp
+dist/ export-ignore

.gitignore

@@ -146,3 +146,7 @@ x509.genkey
 
 # Clang's compilation database file
 /compile_commands.json
+
+# Tencent dist files
+/dist/rpm
+/dist/workdir

Documentation/ABI/testing/sysfs-bus-iio

@@ -1566,7 +1566,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw
 KernelVersion:	4.3
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Raw (unscaled no offset etc.) percentage reading of a substance.
+		Raw (unscaled no offset etc.) reading of a substance. Units
+		after application of scale and offset are percents.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistance_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw

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

@@ -196,6 +196,12 @@ Description:
 		does not reflect it. Likewise, if one enables a deep state but a
 		lighter state still is disabled, then this has no effect.
 
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/default_status
+Date:		December 2019
+KernelVersion:	v5.6
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RO) The default status of this state, "enabled" or "disabled".
 
 What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/residency
 Date:		March 2014
@@ -486,6 +492,7 @@ 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/device-mapper/dm-integrity.rst

@@ -177,6 +177,12 @@ bitmap_flush_interval:number
 	The bitmap flush interval in milliseconds. The metadata buffers
 	are synchronized when this interval expires.
 
+legacy_recalculate
+	Allow recalculating of volumes with HMAC keys. This is disabled by
+	default for security reasons - an attacker could modify the volume,
+	set recalc_sector to zero, and the kernel would not detect the
+	modification.
+
 
 The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can
 be changed when reloading the target (load an inactive table and swap the

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/iostats.rst

@@ -99,7 +99,7 @@ Field 10 -- # of milliseconds spent doing I/Os
 
     Since 5.0 this field counts jiffies when at least one request was
     started or completed. If request runs more than 2 jiffies then some
-    I/O time will not be accounted unless there are other requests.
+    I/O time might be not accounted in case of concurrent requests.
 
 Field 11 -- weighted # of milliseconds spent doing I/Os
     This field is incremented at each I/O start, I/O completion, I/O
@@ -133,6 +133,9 @@ are summed (possibly overflowing the unsigned long variable they are
 summed to) and the result given to the user.  There is no convenient
 user interface for accessing the per-CPU counters themselves.
 
+Since 4.19 request times are measured with nanoseconds precision and
+truncated to milliseconds before showing in this interface.
+
 Disks vs Partitions
 -------------------
 

Documentation/admin-guide/kernel-parameters.txt

@@ -567,7 +567,7 @@
 			loops can be debugged more effectively on production
 			systems.
 
-	clearcpuid=BITNUM [X86]
+	clearcpuid=BITNUM[,BITNUM...] [X86]
 			Disable CPUID feature X for the kernel. See
 			arch/x86/include/asm/cpufeatures.h for the valid bit
 			numbers. Note the Linux specific bits are not necessarily
@@ -2667,6 +2667,8 @@
 					       mds=off [X86]
 					       tsx_async_abort=off [X86]
 					       kvm.nx_huge_pages=off [X86]
+					       no_entry_flush [PPC]
+					       no_uaccess_flush [PPC]
 
 				Exceptions:
 					       This does not have any effect on
@@ -2741,7 +2743,7 @@
 			<name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
 
 	mtdparts=	[MTD]
-			See drivers/mtd/cmdlinepart.c.
+			See drivers/mtd/parsers/cmdlinepart.c
 
 	multitce=off	[PPC]  This parameter disables the use of the pSeries
 			firmware feature for updating multiple TCE entries
@@ -2936,6 +2938,8 @@
 	no5lvl		[X86-64] Disable 5-level paging mode. Forces
 			kernel to use 4-level paging instead.
 
+	nofsgsbase	[X86] Disables FSGSBASE instructions.
+
 	no_console_suspend
 			[HW] Never suspend the console
 			Disable suspending of consoles during suspend and
@@ -2989,6 +2993,8 @@
 
 	noefi		Disable EFI runtime services support.
 
+	no_entry_flush  [PPC] Don't flush the L1-D cache when entering the kernel.
+
 	noexec		[IA-64]
 
 	noexec		[X86]
@@ -3038,6 +3044,9 @@
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
 
+	no_uaccess_flush
+	                [PPC] Don't flush the L1-D cache after accessing user data.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -3171,6 +3180,8 @@
 
 	nosep		[BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.
 
+	nosgx		[X86-64,SGX] Disables Intel SGX kernel support.
+
 	nosmp		[SMP] Tells an SMP kernel to act as a UP kernel,
 			and disable the IO APIC.  legacy for "maxcpus=0".
 
@@ -3577,6 +3588,8 @@
 			even if the platform doesn't give the OS permission to
 			use them.  This may cause conflicts if the platform
 			also tries to use these services.
+		dpc-native	Use native PCIe service for DPC only.  May
+				cause conflicts if firmware uses AER or DPC.
 		compat	Disable native PCIe services (PME, AER, DPC, PCIe
 			hotplug).
 
@@ -3771,6 +3784,14 @@
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.
 
+qspinlock.numa_spinlock_threshold_ns=	[NUMA, PV_OPS]
+			Set the time threshold in nanoseconds for the
+			number of intra-node lock hand-offs before the
+			NUMA-aware spinlock is forced to be passed to
+			a thread on another NUMA node. Smaller values
+			result in a more fair, but less performant spinlock,
+			and vice versa. The default value is 1000000 (=1ms).
+
 	quiet		[KNL] Disable most log messages
 
 	r128=		[HW,DRM]
@@ -4579,6 +4600,26 @@
 	spia_pedr=
 	spia_peddr=
 
+	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
@@ -5005,8 +5046,7 @@
 
 	usbcore.old_scheme_first=
 			[USB] Start with the old device initialization
-			scheme,  applies only to low and full-speed devices
+			scheme (default 0 = off).
-			 (default 0 = off).
 
 	usbcore.usbfs_memory_mb=
 			[USB] Memory limit (in MB) for buffers allocated by
@@ -5125,6 +5165,7 @@
 					device);
 				j = NO_REPORT_LUNS (don't use report luns
 					command, uas only);
+				k = NO_SAME (do not use WRITE_SAME, uas only)
 				l = NOT_LOCKABLE (don't try to lock and
 					unlock ejectable media, not on uas);
 				m = MAX_SECTORS_64 (don't transfer more
@@ -5425,6 +5466,10 @@
 			This option is obsoleted by the "nopv" option, which
 			has equivalent effect for XEN platform.
 
+	xen_no_vector_callback
+			[KNL,X86,XEN] Disable the vector callback for Xen
+			event channel interrupts.
+
 	xen_scrub_pages=	[XEN]
 			Boolean option to control scrubbing pages before giving them back
 			to Xen, for use by other domains. Can be also changed at runtime
@@ -5443,6 +5488,18 @@
 			as generic guest with no PV drivers. Currently support
 			XEN HVM, KVM, HYPER_V and VMWARE guest.
 
+	xen.event_eoi_delay=	[XEN]
+			How long to delay EOI handling in case of event
+			storms (jiffies). Default is 10.
+
+	xen.event_loop_timeout=	[XEN]
+			After which time (jiffies) the event handling loop
+			should start to delay EOI handling. Default is 2.
+	nopvspin	[X86,XEN,KVM]
+			Disables the qspinlock slow path using PV optimizations
+			which allow the hypervisor to 'idle' the guest on lock
+			contention.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

Documentation/admin-guide/pm/cpuidle.rst

@@ -506,6 +506,9 @@ object corresponding to it, as follows:
 ``disable``
 	Whether or not this idle state is disabled.
 
+``default_status``
+	The default status of this state, "enabled" or "disabled".
+
 ``latency``
 	Exit latency of the idle state in microseconds.
 

Documentation/admin-guide/pm/intel_idle.rst

@@ -0,0 +1,246 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+==============================================
+``intel_idle`` CPU Idle Time Management Driver
+==============================================
+
+:Copyright: |copy| 2020 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+
+General Information
+===================
+
+``intel_idle`` is a part of the
+:doc:`CPU idle time management subsystem <cpuidle>` in the Linux kernel
+(``CPUIdle``).  It is the default CPU idle time management driver for the
+Nehalem and later generations of Intel processors, but the level of support for
+a particular processor model in it depends on whether or not it recognizes that
+processor model and may also depend on information coming from the platform
+firmware.  [To understand ``intel_idle`` it is necessary to know how ``CPUIdle``
+works in general, so this is the time to get familiar with :doc:`cpuidle` if you
+have not done that yet.]
+
+``intel_idle`` uses the ``MWAIT`` instruction to inform the processor that the
+logical CPU executing it is idle and so it may be possible to put some of the
+processor's functional blocks into low-power states.  That instruction takes two
+arguments (passed in the ``EAX`` and ``ECX`` registers of the target CPU), the
+first of which, referred to as a *hint*, can be used by the processor to
+determine what can be done (for details refer to Intel Software Developer’s
+Manual [1]_).  Accordingly, ``intel_idle`` refuses to work with processors in
+which the support for the ``MWAIT`` instruction has been disabled (for example,
+via the platform firmware configuration menu) or which do not support that
+instruction at all.
+
+``intel_idle`` is not modular, so it cannot be unloaded, which means that the
+only way to pass early-configuration-time parameters to it is via the kernel
+command line.
+
+
+.. _intel-idle-enumeration-of-states:
+
+Enumeration of Idle States
+==========================
+
+Each ``MWAIT`` hint value is interpreted by the processor as a license to
+reconfigure itself in a certain way in order to save energy.  The processor
+configurations (with reduced power draw) resulting from that are referred to
+as C-states (in the ACPI terminology) or idle states.  The list of meaningful
+``MWAIT`` hint values and idle states (i.e. low-power configurations of the
+processor) corresponding to them depends on the processor model and it may also
+depend on the configuration of the platform.
+
+In order to create a list of available idle states required by the ``CPUIdle``
+subsystem (see :ref:`idle-states-representation` in :doc:`cpuidle`),
+``intel_idle`` can use two sources of information: static tables of idle states
+for different processor models included in the driver itself and the ACPI tables
+of the system.  The former are always used if the processor model at hand is
+recognized by ``intel_idle`` and the latter are used if that is required for
+the given processor model (which is the case for all server processor models
+recognized by ``intel_idle``) or if the processor model is not recognized.
+
+If the ACPI tables are going to be used for building the list of available idle
+states, ``intel_idle`` first looks for a ``_CST`` object under one of the ACPI
+objects corresponding to the CPUs in the system (refer to the ACPI specification
+[2]_ for the description of ``_CST`` and its output package).  Because the
+``CPUIdle`` subsystem expects that the list of idle states supplied by the
+driver will be suitable for all of the CPUs handled by it and ``intel_idle`` is
+registered as the ``CPUIdle`` driver for all of the CPUs in the system, the
+driver looks for the first ``_CST`` object returning at least one valid idle
+state description and such that all of the idle states included in its return
+package are of the FFH (Functional Fixed Hardware) type, which means that the
+``MWAIT`` instruction is expected to be used to tell the processor that it can
+enter one of them.  The return package of that ``_CST`` is then assumed to be
+applicable to all of the other CPUs in the system and the idle state
+descriptions extracted from it are stored in a preliminary list of idle states
+coming from the ACPI tables.  [This step is skipped if ``intel_idle`` is
+configured to ignore the ACPI tables; see `below <intel-idle-parameters_>`_.]
+
+Next, the first (index 0) entry in the list of available idle states is
+initialized to represent a "polling idle state" (a pseudo-idle state in which
+the target CPU continuously fetches and executes instructions), and the
+subsequent (real) idle state entries are populated as follows.
+
+If the processor model at hand is recognized by ``intel_idle``, there is a
+(static) table of idle state descriptions for it in the driver.  In that case,
+the "internal" table is the primary source of information on idle states and the
+information from it is copied to the final list of available idle states.  If
+using the ACPI tables for the enumeration of idle states is not required
+(depending on the processor model), all of the listed idle state are enabled by
+default (so all of them will be taken into consideration by ``CPUIdle``
+governors during CPU idle state selection).  Otherwise, some of the listed idle
+states may not be enabled by default if there are no matching entries in the
+preliminary list of idle states coming from the ACPI tables.  In that case user
+space still can enable them later (on a per-CPU basis) with the help of
+the ``disable`` idle state attribute in ``sysfs`` (see
+:ref:`idle-states-representation` in :doc:`cpuidle`).  This basically means that
+the idle states "known" to the driver may not be enabled by default if they have
+not been exposed by the platform firmware (through the ACPI tables).
+
+If the given processor model is not recognized by ``intel_idle``, but it
+supports ``MWAIT``, the preliminary list of idle states coming from the ACPI
+tables is used for building the final list that will be supplied to the
+``CPUIdle`` core during driver registration.  For each idle state in that list,
+the description, ``MWAIT`` hint and exit latency are copied to the corresponding
+entry in the final list of idle states.  The name of the idle state represented
+by it (to be returned by the ``name`` idle state attribute in ``sysfs``) is
+"CX_ACPI", where X is the index of that idle state in the final list (note that
+the minimum value of X is 1, because 0 is reserved for the "polling" state), and
+its target residency is based on the exit latency value.  Specifically, for
+C1-type idle states the exit latency value is also used as the target residency
+(for compatibility with the majority of the "internal" tables of idle states for
+various processor models recognized by ``intel_idle``) and for the other idle
+state types (C2 and C3) the target residency value is 3 times the exit latency
+(again, that is because it reflects the target residency to exit latency ratio
+in the majority of cases for the processor models recognized by ``intel_idle``).
+All of the idle states in the final list are enabled by default in this case.
+
+
+.. _intel-idle-initialization:
+
+Initialization
+==============
+
+The initialization of ``intel_idle`` starts with checking if the kernel command
+line options forbid the use of the ``MWAIT`` instruction.  If that is the case,
+an error code is returned right away.
+
+The next step is to check whether or not the processor model is known to the
+driver, which determines the idle states enumeration method (see
+`above <intel-idle-enumeration-of-states_>`_), and whether or not the processor
+supports ``MWAIT`` (the initialization fails if that is not the case).  Then,
+the ``MWAIT`` support in the processor is enumerated through ``CPUID`` and the
+driver initialization fails if the level of support is not as expected (for
+example, if the total number of ``MWAIT`` substates returned is 0).
+
+Next, if the driver is not configured to ignore the ACPI tables (see
+`below <intel-idle-parameters_>`_), the idle states information provided by the
+platform firmware is extracted from them.
+
+Then, ``CPUIdle`` device objects are allocated for all CPUs and the list of
+available idle states is created as explained
+`above <intel-idle-enumeration-of-states_>`_.
+
+Finally, ``intel_idle`` is registered with the help of cpuidle_register_driver()
+as the ``CPUIdle`` driver for all CPUs in the system and a CPU online callback
+for configuring individual CPUs is registered via cpuhp_setup_state(), which
+(among other things) causes the callback routine to be invoked for all of the
+CPUs present in the system at that time (each CPU executes its own instance of
+the callback routine).  That routine registers a ``CPUIdle`` device for the CPU
+running it (which enables the ``CPUIdle`` subsystem to operate that CPU) and
+optionally performs some CPU-specific initialization actions that may be
+required for the given processor model.
+
+
+.. _intel-idle-parameters:
+
+Kernel Command Line Options and Module Parameters
+=================================================
+
+The *x86* architecture support code recognizes three kernel command line
+options related to CPU idle time management: ``idle=poll``, ``idle=halt``,
+and ``idle=nomwait``.  If any of them is present in the kernel command line, the
+``MWAIT`` instruction is not allowed to be used, so the initialization of
+``intel_idle`` will fail.
+
+Apart from that there are two module parameters recognized by ``intel_idle``
+itself that can be set via the kernel command line (they cannot be updated via
+sysfs, so that is the only way to change their values).
+
+The ``max_cstate`` parameter value is the maximum idle state index in the list
+of idle states supplied to the ``CPUIdle`` core during the registration of the
+driver.  It is also the maximum number of regular (non-polling) idle states that
+can be used by ``intel_idle``, so the enumeration of idle states is terminated
+after finding that number of usable idle states (the other idle states that
+potentially might have been used if ``max_cstate`` had been greater are not
+taken into consideration at all).  Setting ``max_cstate`` can prevent
+``intel_idle`` from exposing idle states that are regarded as "too deep" for
+some reason to the ``CPUIdle`` core, but it does so by making them effectively
+invisible until the system is shut down and started again which may not always
+be desirable.  In practice, it is only really necessary to do that if the idle
+states in question cannot be enabled during system startup, because in the
+working state of the system the CPU power management quality of service (PM
+QoS) feature can be used to prevent ``CPUIdle`` from touching those idle states
+even if they have been enumerated (see :ref:`cpu-pm-qos` in :doc:`cpuidle`).
+Setting ``max_cstate`` to 0 causes the ``intel_idle`` initialization to fail.
+
+The ``noacpi`` module parameter (which is recognized by ``intel_idle`` if the
+kernel has been configured with ACPI support), can be set to make the driver
+ignore the system's ACPI tables entirely (it is unset by default).
+
+
+.. _intel-idle-core-and-package-idle-states:
+
+Core and Package Levels of Idle States
+======================================
+
+Typically, in a processor supporting the ``MWAIT`` instruction there are (at
+least) two levels of idle states (or C-states).  One level, referred to as
+"core C-states", covers individual cores in the processor, whereas the other
+level, referred to as "package C-states", covers the entire processor package
+and it may also involve other components of the system (GPUs, memory
+controllers, I/O hubs etc.).
+
+Some of the ``MWAIT`` hint values allow the processor to use core C-states only
+(most importantly, that is the case for the ``MWAIT`` hint value corresponding
+to the ``C1`` idle state), but the majority of them give it a license to put
+the target core (i.e. the core containing the logical CPU executing ``MWAIT``
+with the given hint value) into a specific core C-state and then (if possible)
+to enter a specific package C-state at the deeper level.  For example, the
+``MWAIT`` hint value representing the ``C3`` idle state allows the processor to
+put the target core into the low-power state referred to as "core ``C3``" (or
+``CC3``), which happens if all of the logical CPUs (SMT siblings) in that core
+have executed ``MWAIT`` with the ``C3`` hint value (or with a hint value
+representing a deeper idle state), and in addition to that (in the majority of
+cases) it gives the processor a license to put the entire package (possibly
+including some non-CPU components such as a GPU or a memory controller) into the
+low-power state referred to as "package ``C3``" (or ``PC3``), which happens if
+all of the cores have gone into the ``CC3`` state and (possibly) some additional
+conditions are satisfied (for instance, if the GPU is covered by ``PC3``, it may
+be required to be in a certain GPU-specific low-power state for ``PC3`` to be
+reachable).
+
+As a rule, there is no simple way to make the processor use core C-states only
+if the conditions for entering the corresponding package C-states are met, so
+the logical CPU executing ``MWAIT`` with a hint value that is not core-level
+only (like for ``C1``) must always assume that this may cause the processor to
+enter a package C-state.  [That is why the exit latency and target residency
+values corresponding to the majority of ``MWAIT`` hint values in the "internal"
+tables of idle states in ``intel_idle`` reflect the properties of package
+C-states.]  If using package C-states is not desirable at all, either
+:ref:`PM QoS <cpu-pm-qos>` or the ``max_cstate`` module parameter of
+``intel_idle`` described `above <intel-idle-parameters_>`_ must be used to
+restrict the range of permissible idle states to the ones with core-level only
+``MWAIT`` hint values (like ``C1``).
+
+
+References
+==========
+
+.. [1] *Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 2B*,
+       https://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-vol-2b-manual.html
+
+.. [2] *Advanced Configuration and Power Interface (ACPI) Specification*,
+       https://uefi.org/specifications

Documentation/admin-guide/pm/working-state.rst

@@ -8,6 +8,7 @@ Working-State Power Management
    :maxdepth: 2
 
    cpuidle
+   intel_idle
    cpufreq
    intel_pstate
    intel_epb

Documentation/arm64/silicon-errata.rst

@@ -52,6 +52,9 @@ stable kernels.
 | Allwinner      | A64/R18         | UNKNOWN1        | SUN50I_ERRATUM_UNKNOWN1     |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| Ampere         | Altra           | #82288          | ALTRA_ERRATUM_82288         |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319        |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319        |
@@ -88,6 +91,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

Documentation/asm-annotations.rst

@@ -0,0 +1,216 @@
+Assembler Annotations
+=====================
+
+Copyright (c) 2017-2019 Jiri Slaby
+
+This document describes the new macros for annotation of data and code in
+assembly. In particular, it contains information about ``SYM_FUNC_START``,
+``SYM_FUNC_END``, ``SYM_CODE_START``, and similar.
+
+Rationale
+---------
+Some code like entries, trampolines, or boot code needs to be written in
+assembly. The same as in C, such code is grouped into functions and
+accompanied with data. Standard assemblers do not force users into precisely
+marking these pieces as code, data, or even specifying their length.
+Nevertheless, assemblers provide developers with such annotations to aid
+debuggers throughout assembly. On top of that, developers also want to mark
+some functions as *global* in order to be visible outside of their translation
+units.
+
+Over time, the Linux kernel has adopted macros from various projects (like
+``binutils``) to facilitate such annotations. So for historic reasons,
+developers have been using ``ENTRY``, ``END``, ``ENDPROC``, and other
+annotations in assembly.  Due to the lack of their documentation, the macros
+are used in rather wrong contexts at some locations. Clearly, ``ENTRY`` was
+intended to denote the beginning of global symbols (be it data or code).
+``END`` used to mark the end of data or end of special functions with
+*non-standard* calling convention. In contrast, ``ENDPROC`` should annotate
+only ends of *standard* functions.
+
+When these macros are used correctly, they help assemblers generate a nice
+object with both sizes and types set correctly. For example, the result of
+``arch/x86/lib/putuser.S``::
+
+   Num:    Value          Size Type    Bind   Vis      Ndx Name
+    25: 0000000000000000    33 FUNC    GLOBAL DEFAULT    1 __put_user_1
+    29: 0000000000000030    37 FUNC    GLOBAL DEFAULT    1 __put_user_2
+    32: 0000000000000060    36 FUNC    GLOBAL DEFAULT    1 __put_user_4
+    35: 0000000000000090    37 FUNC    GLOBAL DEFAULT    1 __put_user_8
+
+This is not only important for debugging purposes. When there are properly
+annotated objects like this, tools can be run on them to generate more useful
+information. In particular, on properly annotated objects, ``objtool`` can be
+run to check and fix the object if needed. Currently, ``objtool`` can report
+missing frame pointer setup/destruction in functions. It can also
+automatically generate annotations for :doc:`ORC unwinder <x86/orc-unwinder>`
+for most code. Both of these are especially important to support reliable
+stack traces which are in turn necessary for :doc:`Kernel live patching
+<livepatch/livepatch>`.
+
+Caveat and Discussion
+---------------------
+As one might realize, there were only three macros previously. That is indeed
+insufficient to cover all the combinations of cases:
+
+* standard/non-standard function
+* code/data
+* global/local symbol
+
+There was a discussion_ and instead of extending the current ``ENTRY/END*``
+macros, it was decided that brand new macros should be introduced instead::
+
+    So how about using macro names that actually show the purpose, instead
+    of importing all the crappy, historic, essentially randomly chosen
+    debug symbol macro names from the binutils and older kernels?
+
+.. _discussion: https://lkml.kernel.org/r/20170217104757.28588-1-jslaby@suse.cz
+
+Macros Description
+------------------
+
+The new macros are prefixed with the ``SYM_`` prefix and can be divided into
+three main groups:
+
+1. ``SYM_FUNC_*`` -- to annotate C-like functions. This means functions with
+   standard C calling conventions, i.e. the stack contains a return address at
+   the predefined place and a return from the function can happen in a
+   standard way. When frame pointers are enabled, save/restore of frame
+   pointer shall happen at the start/end of a function, respectively, too.
+
+   Checking tools like ``objtool`` should ensure such marked functions conform
+   to these rules. The tools can also easily annotate these functions with
+   debugging information (like *ORC data*) automatically.
+
+2. ``SYM_CODE_*`` -- special functions called with special stack. Be it
+   interrupt handlers with special stack content, trampolines, or startup
+   functions.
+
+   Checking tools mostly ignore checking of these functions. But some debug
+   information still can be generated automatically. For correct debug data,
+   this code needs hints like ``UNWIND_HINT_REGS`` provided by developers.
+
+3. ``SYM_DATA*`` -- obviously data belonging to ``.data`` sections and not to
+   ``.text``. Data do not contain instructions, so they have to be treated
+   specially by the tools: they should not treat the bytes as instructions,
+   nor assign any debug information to them.
+
+Instruction Macros
+~~~~~~~~~~~~~~~~~~
+This section covers ``SYM_FUNC_*`` and ``SYM_CODE_*`` enumerated above.
+
+* ``SYM_FUNC_START`` and ``SYM_FUNC_START_LOCAL`` are supposed to be **the
+  most frequent markings**. They are used for functions with standard calling
+  conventions -- global and local. Like in C, they both align the functions to
+  architecture specific ``__ALIGN`` bytes. There are also ``_NOALIGN`` variants
+  for special cases where developers do not want this implicit alignment.
+
+  ``SYM_FUNC_START_WEAK`` and ``SYM_FUNC_START_WEAK_NOALIGN`` markings are
+  also offered as an assembler counterpart to the *weak* attribute known from
+  C.
+
+  All of these **shall** be coupled with ``SYM_FUNC_END``. First, it marks
+  the sequence of instructions as a function and computes its size to the
+  generated object file. Second, it also eases checking and processing such
+  object files as the tools can trivially find exact function boundaries.
+
+  So in most cases, developers should write something like in the following
+  example, having some asm instructions in between the macros, of course::
+
+    SYM_FUNC_START(function_hook)
+        ... asm insns ...
+    SYM_FUNC_END(function_hook)
+
+  In fact, this kind of annotation corresponds to the now deprecated ``ENTRY``
+  and ``ENDPROC`` macros.
+
+* ``SYM_FUNC_START_ALIAS`` and ``SYM_FUNC_START_LOCAL_ALIAS`` serve for those
+  who decided to have two or more names for one function. The typical use is::
+
+    SYM_FUNC_START_ALIAS(__memset)
+    SYM_FUNC_START(memset)
+        ... asm insns ...
+    SYM_FUNC_END(memset)
+    SYM_FUNC_END_ALIAS(__memset)
+
+  In this example, one can call ``__memset`` or ``memset`` with the same
+  result, except the debug information for the instructions is generated to
+  the object file only once -- for the non-``ALIAS`` case.
+
+* ``SYM_CODE_START`` and ``SYM_CODE_START_LOCAL`` should be used only in
+  special cases -- if you know what you are doing. This is used exclusively
+  for interrupt handlers and similar where the calling convention is not the C
+  one. ``_NOALIGN`` variants exist too. The use is the same as for the ``FUNC``
+  category above::
+
+    SYM_CODE_START_LOCAL(bad_put_user)
+        ... asm insns ...
+    SYM_CODE_END(bad_put_user)
+
+  Again, every ``SYM_CODE_START*`` **shall** be coupled by ``SYM_CODE_END``.
+
+  To some extent, this category corresponds to deprecated ``ENTRY`` and
+  ``END``. Except ``END`` had several other meanings too.
+
+* ``SYM_INNER_LABEL*`` is used to denote a label inside some
+  ``SYM_{CODE,FUNC}_START`` and ``SYM_{CODE,FUNC}_END``.  They are very similar
+  to C labels, except they can be made global. An example of use::
+
+    SYM_CODE_START(ftrace_caller)
+        /* save_mcount_regs fills in first two parameters */
+        ...
+
+    SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
+        /* Load the ftrace_ops into the 3rd parameter */
+        ...
+
+    SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
+        call ftrace_stub
+        ...
+        retq
+    SYM_CODE_END(ftrace_caller)
+
+Data Macros
+~~~~~~~~~~~
+Similar to instructions, there is a couple of macros to describe data in the
+assembly.
+
+* ``SYM_DATA_START`` and ``SYM_DATA_START_LOCAL`` mark the start of some data
+  and shall be used in conjunction with either ``SYM_DATA_END``, or
+  ``SYM_DATA_END_LABEL``. The latter adds also a label to the end, so that
+  people can use ``lstack`` and (local) ``lstack_end`` in the following
+  example::
+
+    SYM_DATA_START_LOCAL(lstack)
+        .skip 4096
+    SYM_DATA_END_LABEL(lstack, SYM_L_LOCAL, lstack_end)
+
+* ``SYM_DATA`` and ``SYM_DATA_LOCAL`` are variants for simple, mostly one-line
+  data::
+
+    SYM_DATA(HEAP,     .long rm_heap)
+    SYM_DATA(heap_end, .long rm_stack)
+
+  In the end, they expand to ``SYM_DATA_START`` with ``SYM_DATA_END``
+  internally.
+
+Support Macros
+~~~~~~~~~~~~~~
+All the above reduce themselves to some invocation of ``SYM_START``,
+``SYM_END``, or ``SYM_ENTRY`` at last. Normally, developers should avoid using
+these.
+
+Further, in the above examples, one could see ``SYM_L_LOCAL``. There are also
+``SYM_L_GLOBAL`` and ``SYM_L_WEAK``. All are intended to denote linkage of a
+symbol marked by them. They are used either in ``_LABEL`` variants of the
+earlier macros, or in ``SYM_START``.
+
+
+Overriding Macros
+~~~~~~~~~~~~~~~~~
+Architecture can also override any of the macros in their own
+``asm/linkage.h``, including macros specifying the type of a symbol
+(``SYM_T_FUNC``, ``SYM_T_OBJECT``, and ``SYM_T_NONE``).  As every macro
+described in this file is surrounded by ``#ifdef`` + ``#endif``, it is enough
+to define the macros differently in the aforementioned architecture-dependent
+header.

Documentation/bpf/prog_flow_dissector.rst

@@ -142,3 +142,6 @@ BPF flow dissector doesn't support exporting all the metadata that in-kernel
 C-based implementation can export. Notable example is single VLAN (802.1Q)
 and double VLAN (802.1AD) tags. Please refer to the ``struct bpf_flow_keys``
 for a set of information that's currently can be exported from the BPF context.
+
+When BPF flow dissector is attached to the root network namespace (machine-wide
+policy), users can't override it in their child network namespaces.

Documentation/bpf/ringbuf.rst

@@ -0,0 +1,209 @@
+===============
+BPF ring buffer
+===============
+
+This document describes BPF ring buffer design, API, and implementation details.
+
+.. contents::
+    :local:
+    :depth: 2
+
+Motivation
+----------
+
+There are two distinctive motivators for this work, which are not satisfied by
+existing perf buffer, which prompted creation of a new ring buffer
+implementation.
+
+- more efficient memory utilization by sharing ring buffer across CPUs;
+- preserving ordering of events that happen sequentially in time, even across
+  multiple CPUs (e.g., fork/exec/exit events for a task).
+
+These two problems are independent, but perf buffer fails to satisfy both.
+Both are a result of a choice to have per-CPU perf ring buffer.  Both can be
+also solved by having an MPSC implementation of ring buffer. The ordering
+problem could technically be solved for perf buffer with some in-kernel
+counting, but given the first one requires an MPSC buffer, the same solution
+would solve the second problem automatically.
+
+Semantics and APIs
+------------------
+
+Single ring buffer is presented to BPF programs as an instance of BPF map of
+type ``BPF_MAP_TYPE_RINGBUF``. Two other alternatives considered, but
+ultimately rejected.
+
+One way would be to, similar to ``BPF_MAP_TYPE_PERF_EVENT_ARRAY``, make
+``BPF_MAP_TYPE_RINGBUF`` could represent an array of ring buffers, but not
+enforce "same CPU only" rule. This would be more familiar interface compatible
+with existing perf buffer use in BPF, but would fail if application needed more
+advanced logic to lookup ring buffer by arbitrary key.
+``BPF_MAP_TYPE_HASH_OF_MAPS`` addresses this with current approach.
+Additionally, given the performance of BPF ringbuf, many use cases would just
+opt into a simple single ring buffer shared among all CPUs, for which current
+approach would be an overkill.
+
+Another approach could introduce a new concept, alongside BPF map, to represent
+generic "container" object, which doesn't necessarily have key/value interface
+with lookup/update/delete operations. This approach would add a lot of extra
+infrastructure that has to be built for observability and verifier support. It
+would also add another concept that BPF developers would have to familiarize
+themselves with, new syntax in libbpf, etc. But then would really provide no
+additional benefits over the approach of using a map.  ``BPF_MAP_TYPE_RINGBUF``
+doesn't support lookup/update/delete operations, but so doesn't few other map
+types (e.g., queue and stack; array doesn't support delete, etc).
+
+The approach chosen has an advantage of re-using existing BPF map
+infrastructure (introspection APIs in kernel, libbpf support, etc), being
+familiar concept (no need to teach users a new type of object in BPF program),
+and utilizing existing tooling (bpftool). For common scenario of using a single
+ring buffer for all CPUs, it's as simple and straightforward, as would be with
+a dedicated "container" object. On the other hand, by being a map, it can be
+combined with ``ARRAY_OF_MAPS`` and ``HASH_OF_MAPS`` map-in-maps to implement
+a wide variety of topologies, from one ring buffer for each CPU (e.g., as
+a replacement for perf buffer use cases), to a complicated application
+hashing/sharding of ring buffers (e.g., having a small pool of ring buffers
+with hashed task's tgid being a look up key to preserve order, but reduce
+contention).
+
+Key and value sizes are enforced to be zero. ``max_entries`` is used to specify
+the size of ring buffer and has to be a power of 2 value.
+
+There are a bunch of similarities between perf buffer
+(``BPF_MAP_TYPE_PERF_EVENT_ARRAY``) and new BPF ring buffer semantics:
+
+- variable-length records;
+- if there is no more space left in ring buffer, reservation fails, no
+  blocking;
+- memory-mappable data area for user-space applications for ease of
+  consumption and high performance;
+- epoll notifications for new incoming data;
+- but still the ability to do busy polling for new data to achieve the
+  lowest latency, if necessary.
+
+BPF ringbuf provides two sets of APIs to BPF programs:
+
+- ``bpf_ringbuf_output()`` allows to *copy* data from one place to a ring
+  buffer, similarly to ``bpf_perf_event_output()``;
+- ``bpf_ringbuf_reserve()``/``bpf_ringbuf_commit()``/``bpf_ringbuf_discard()``
+  APIs split the whole process into two steps. First, a fixed amount of space
+  is reserved. If successful, a pointer to a data inside ring buffer data
+  area is returned, which BPF programs can use similarly to a data inside
+  array/hash maps. Once ready, this piece of memory is either committed or
+  discarded. Discard is similar to commit, but makes consumer ignore the
+  record.
+
+``bpf_ringbuf_output()`` has disadvantage of incurring extra memory copy,
+because record has to be prepared in some other place first. But it allows to
+submit records of the length that's not known to verifier beforehand. It also
+closely matches ``bpf_perf_event_output()``, so will simplify migration
+significantly.
+
+``bpf_ringbuf_reserve()`` avoids the extra copy of memory by providing a memory
+pointer directly to ring buffer memory. In a lot of cases records are larger
+than BPF stack space allows, so many programs have use extra per-CPU array as
+a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs
+completely. But in exchange, it only allows a known constant size of memory to
+be reserved, such that verifier can verify that BPF program can't access memory
+outside its reserved record space. bpf_ringbuf_output(), while slightly slower
+due to extra memory copy, covers some use cases that are not suitable for
+``bpf_ringbuf_reserve()``.
+
+The difference between commit and discard is very small. Discard just marks
+a record as discarded, and such records are supposed to be ignored by consumer
+code. Discard is useful for some advanced use-cases, such as ensuring
+all-or-nothing multi-record submission, or emulating temporary
+``malloc()``/``free()`` within single BPF program invocation.
+
+Each reserved record is tracked by verifier through existing
+reference-tracking logic, similar to socket ref-tracking. It is thus
+impossible to reserve a record, but forget to submit (or discard) it.
+
+``bpf_ringbuf_query()`` helper allows to query various properties of ring
+buffer.  Currently 4 are supported:
+
+- ``BPF_RB_AVAIL_DATA`` returns amount of unconsumed data in ring buffer;
+- ``BPF_RB_RING_SIZE`` returns the size of ring buffer;
+- ``BPF_RB_CONS_POS``/``BPF_RB_PROD_POS`` returns current logical possition
+  of consumer/producer, respectively.
+
+Returned values are momentarily snapshots of ring buffer state and could be
+off by the time helper returns, so this should be used only for
+debugging/reporting reasons or for implementing various heuristics, that take
+into account highly-changeable nature of some of those characteristics.
+
+One such heuristic might involve more fine-grained control over poll/epoll
+notifications about new data availability in ring buffer. Together with
+``BPF_RB_NO_WAKEUP``/``BPF_RB_FORCE_WAKEUP`` flags for output/commit/discard
+helpers, it allows BPF program a high degree of control and, e.g., more
+efficient batched notifications. Default self-balancing strategy, though,
+should be adequate for most applications and will work reliable and efficiently
+already.
+
+Design and Implementation
+-------------------------
+
+This reserve/commit schema allows a natural way for multiple producers, either
+on different CPUs or even on the same CPU/in the same BPF program, to reserve
+independent records and work with them without blocking other producers. This
+means that if BPF program was interruped by another BPF program sharing the
+same ring buffer, they will both get a record reserved (provided there is
+enough space left) and can work with it and submit it independently. This
+applies to NMI context as well, except that due to using a spinlock during
+reservation, in NMI context, ``bpf_ringbuf_reserve()`` might fail to get
+a lock, in which case reservation will fail even if ring buffer is not full.
+
+The ring buffer itself internally is implemented as a power-of-2 sized
+circular buffer, with two logical and ever-increasing counters (which might
+wrap around on 32-bit architectures, that's not a problem):
+
+- consumer counter shows up to which logical position consumer consumed the
+  data;
+- producer counter denotes amount of data reserved by all producers.
+
+Each time a record is reserved, producer that "owns" the record will
+successfully advance producer counter. At that point, data is still not yet
+ready to be consumed, though. Each record has 8 byte header, which contains the
+length of reserved record, as well as two extra bits: busy bit to denote that
+record is still being worked on, and discard bit, which might be set at commit
+time if record is discarded. In the latter case, consumer is supposed to skip
+the record and move on to the next one. Record header also encodes record's
+relative offset from the beginning of ring buffer data area (in pages). This
+allows ``bpf_ringbuf_commit()``/``bpf_ringbuf_discard()`` to accept only the
+pointer to the record itself, without requiring also the pointer to ring buffer
+itself. Ring buffer memory location will be restored from record metadata
+header. This significantly simplifies verifier, as well as improving API
+usability.
+
+Producer counter increments are serialized under spinlock, so there is
+a strict ordering between reservations. Commits, on the other hand, are
+completely lockless and independent. All records become available to consumer
+in the order of reservations, but only after all previous records where
+already committed. It is thus possible for slow producers to temporarily hold
+off submitted records, that were reserved later.
+
+Reservation/commit/consumer protocol is verified by litmus tests in
+Documentation/litmus_tests/bpf-rb/_.
+
+One interesting implementation bit, that significantly simplifies (and thus
+speeds up as well) implementation of both producers and consumers is how data
+area is mapped twice contiguously back-to-back in the virtual memory. This
+allows to not take any special measures for samples that have to wrap around
+at the end of the circular buffer data area, because the next page after the
+last data page would be first data page again, and thus the sample will still
+appear completely contiguous in virtual memory. See comment and a simple ASCII
+diagram showing this visually in ``bpf_ringbuf_area_alloc()``.
+
+Another feature that distinguishes BPF ringbuf from perf ring buffer is
+a self-pacing notifications of new data being availability.
+``bpf_ringbuf_commit()`` implementation will send a notification of new record
+being available after commit only if consumer has already caught up right up to
+the record being committed. If not, consumer still has to catch up and thus
+will see new data anyways without needing an extra poll notification.
+Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c_) show that
+this allows to achieve a very high throughput without having to resort to
+tricks like "notify only every Nth sample", which are necessary with perf
+buffer. For extreme cases, when BPF program wants more manual control of
+notifications, commit/discard/output helpers accept ``BPF_RB_NO_WAKEUP`` and
+``BPF_RB_FORCE_WAKEUP`` flags, which give full control over notifications of
+data availability, but require extra caution and diligence in using this API.

Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt

@@ -16,6 +16,9 @@ Required properties:
   Documentation/devicetree/bindings/graph.txt. This port should be connected
   to the input port of an attached HDMI or LVDS encoder chip.
 
+Optional properties:
+- pinctrl-names: Contain "default" and "sleep".
+
 Example:
 
 dpi0: dpi@1401d000 {
@@ -26,6 +29,9 @@ dpi0: dpi@1401d000 {
 		 <&mmsys CLK_MM_DPI_ENGINE>,
 		 <&apmixedsys CLK_APMIXED_TVDPLL>;
 	clock-names = "pixel", "engine", "pll";
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&dpi_pin_func>;
+	pinctrl-1 = <&dpi_pin_idle>;
 
 	port {
 		dpi0_out: endpoint {

Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt

@@ -20,8 +20,9 @@ Required properties:
 - gpio-controller : Marks the device node as a GPIO controller
 - interrupts : Interrupt specifier, see interrupt-controller/interrupts.txt
 - interrupt-controller : Mark the GPIO controller as an interrupt-controller
-- ngpios : number of GPIO lines, see gpio.txt
+- ngpios : number of *hardware* GPIO lines, see gpio.txt. This will expose
-  (should be multiple of 8, up to 80 pins)
+  2 software GPIOs per hardware GPIO: one for hardware input, one for hardware
+  output. Up to 80 pins, must be a multiple of 8.
 - clocks : A phandle to the APB clock for SGPM clock division
 - bus-frequency : SGPM CLK frequency
 

Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt

@@ -21,7 +21,7 @@ controller state. The mux controller state is described in
 
 Example:
 	mux: mux-controller {
-		compatible = "mux-gpio";
+		compatible = "gpio-mux";
 		#mux-control-cells = <0>;
 
 		mux-gpios = <&pioA 0 GPIO_ACTIVE_HIGH>,

Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt

@@ -87,7 +87,7 @@ Example:
 		ranges;
 
 		/* APU<->RPU0 IPI mailbox controller */
-		ipi_mailbox_rpu0: mailbox@ff90400 {
+		ipi_mailbox_rpu0: mailbox@ff990400 {
 			reg = <0xff990400 0x20>,
 			      <0xff990420 0x20>,
 			      <0xff990080 0x20>,

Documentation/devicetree/bindings/mmc/mtk-sd.txt

@@ -49,6 +49,8 @@ Optional properties:
 		     error caused by stop clock(fifo full)
 		     Valid range = [0:0x7]. if not present, default value is 0.
 		     applied to compatible "mediatek,mt2701-mmc".
+- resets: Phandle and reset specifier pair to softreset line of MSDC IP.
+- reset-names: Should be "hrst".
 
 Examples:
 mmc0: mmc@11230000 {

Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.txt

@@ -15,8 +15,15 @@ Required properties:
   - "nvidia,tegra210-sdhci": for Tegra210
   - "nvidia,tegra186-sdhci": for Tegra186
   - "nvidia,tegra194-sdhci": for Tegra194
-- clocks : Must contain one entry, for the module clock.
+- clocks: For Tegra210, Tegra186 and Tegra194 must contain two entries.
-  See ../clocks/clock-bindings.txt for details.
+	  One for the module clock and one for the timeout clock.
+	  For all other Tegra devices, must contain a single entry for
+	  the module clock. See ../clocks/clock-bindings.txt for details.
+- clock-names: For Tegra210, Tegra186 and Tegra194 must contain the
+	       strings 'sdhci' and 'tmclk' to represent the module and
+	       the timeout clocks, respectively.
+	       For all other Tegra devices must contain the string 'sdhci'
+	       to represent the module clock.
 - resets : Must contain an entry for each entry in reset-names.
   See ../reset/reset.txt for details.
 - reset-names : Must include the following entries:
@@ -99,7 +106,7 @@ Optional properties for Tegra210, Tegra186 and Tegra194:
 
 Example:
 sdhci@700b0000 {
-	compatible = "nvidia,tegra210-sdhci", "nvidia,tegra124-sdhci";
+	compatible = "nvidia,tegra124-sdhci";
 	reg = <0x0 0x700b0000 0x0 0x200>;
 	interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 	clocks = <&tegra_car TEGRA210_CLK_SDMMC1>;
@@ -115,3 +122,22 @@ sdhci@700b0000 {
 	nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>;
 	status = "disabled";
 };
+
+sdhci@700b0000 {
+	compatible = "nvidia,tegra210-sdhci";
+	reg = <0x0 0x700b0000 0x0 0x200>;
+	interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&tegra_car TEGRA210_CLK_SDMMC1>,
+		 <&tegra_car TEGRA210_CLK_SDMMC_LEGACY>;
+	clock-names = "sdhci", "tmclk";
+	resets = <&tegra_car 14>;
+	reset-names = "sdhci";
+	pinctrl-names = "sdmmc-3v3", "sdmmc-1v8";
+	pinctrl-0 = <&sdmmc1_3v3>;
+	pinctrl-1 = <&sdmmc1_1v8>;
+	nvidia,pad-autocal-pull-up-offset-3v3 = <0x00>;
+	nvidia,pad-autocal-pull-down-offset-3v3 = <0x7d>;
+	nvidia,pad-autocal-pull-up-offset-1v8 = <0x7b>;
+	nvidia,pad-autocal-pull-down-offset-1v8 = <0x7b>;
+	status = "disabled";
+};

Documentation/devicetree/bindings/net/btusb.txt

@@ -38,7 +38,7 @@ Following example uses irq pin number 3 of gpio0 for out of band wake-on-bt:
 	compatible = "usb1286,204e";
 	reg = <1>;
 	interrupt-parent = <&gpio0>;
-	interrupt-name = "wakeup";
+	interrupt-names = "wakeup";
 	interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
     };
 };

Documentation/devicetree/bindings/net/can/tcan4x5x.txt

@@ -33,7 +33,7 @@ tcan4x5x: tcan4x5x@0 {
 		spi-max-frequency = <10000000>;
 		bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <14 GPIO_ACTIVE_LOW>;
+		interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
 		device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
 		device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>;
 		reset-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;

Documentation/devicetree/bindings/net/ethernet-controller.yaml

@@ -51,7 +51,7 @@ properties:
     description:
       Reference to an nvmem node for the MAC address
 
-  nvmem-cells-names:
+  nvmem-cell-names:
     const: mac-address
 
   phy-connection-type:
@@ -190,6 +190,11 @@ properties:
                 Indicates that full-duplex is used. When absent, half
                 duplex is assumed.
 
+            pause:
+              $ref: /schemas/types.yaml#definitions/flag
+              description:
+                Indicates that pause should be enabled.
+
             asym-pause:
               $ref: /schemas/types.yaml#definitions/flag
               description:

Documentation/devicetree/bindings/net/nfc/nxp-nci.txt

@@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with NPC100 NFC controller on I2C2):
 		clock-frequency = <100000>;
 
 		interrupt-parent = <&gpio1>;
-		interrupts = <29 GPIO_ACTIVE_HIGH>;
+		interrupts = <29 IRQ_TYPE_LEVEL_HIGH>;
 
 		enable-gpios = <&gpio0 30 GPIO_ACTIVE_HIGH>;
 		firmware-gpios = <&gpio0 31 GPIO_ACTIVE_HIGH>;

Documentation/devicetree/bindings/net/nfc/pn544.txt

@@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with PN544 on I2C2):
 		clock-frequency = <400000>;
 
 		interrupt-parent = <&gpio1>;
-		interrupts = <17 GPIO_ACTIVE_HIGH>;
+		interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
 
 		enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
 		firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;

Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.txt

@@ -118,7 +118,7 @@ Tegra194:
 --------
 
 	pcie@14180000 {
-		compatible = "nvidia,tegra194-pcie", "snps,dw-pcie";
+		compatible = "nvidia,tegra194-pcie";
 		power-domains = <&bpmp TEGRA194_POWER_DOMAIN_PCIEX8B>;
 		reg = <0x00 0x14180000 0x0 0x00020000   /* appl registers (128K)      */
 		       0x00 0x38000000 0x0 0x00040000   /* configuration space (256K) */

Documentation/devicetree/bindings/sound/wm8994.txt

@@ -14,9 +14,15 @@ Required properties:
   - #gpio-cells : Must be 2. The first cell is the pin number and the
     second cell is used to specify optional parameters (currently unused).
 
-  - AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, CPVDD-supply,
+  - power supplies for the device, as covered in
-    SPKVDD1-supply, SPKVDD2-supply : power supplies for the device, as covered
+    Documentation/devicetree/bindings/regulator/regulator.txt, depending
-    in Documentation/devicetree/bindings/regulator/regulator.txt
+    on compatible:
+    - for wlf,wm1811 and wlf,wm8958:
+      AVDD1-supply, AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply,
+      DCVDD-supply, CPVDD-supply, SPKVDD1-supply, SPKVDD2-supply
+    - for wlf,wm8994:
+      AVDD1-supply, AVDD2-supply, DBVDD-supply, DCVDD-supply, CPVDD-supply,
+      SPKVDD1-supply, SPKVDD2-supply
 
 Optional properties:
 
@@ -73,11 +79,11 @@ wm8994: codec@1a {
 
 	lineout1-se;
 
+	AVDD1-supply = <&regulator>;
 	AVDD2-supply = <&regulator>;
 	CPVDD-supply = <&regulator>;
-	DBVDD1-supply = <&regulator>;
+	DBVDD-supply = <&regulator>;
-	DBVDD2-supply = <&regulator>;
+	DCVDD-supply = <&regulator>;
-	DBVDD3-supply = <&regulator>;
 	SPKVDD1-supply = <&regulator>;
 	SPKVDD2-supply = <&regulator>;
 };

Documentation/devicetree/bindings/usb/dwc3.txt

@@ -75,6 +75,8 @@ Optional properties:
 			from P0 to P1/P2/P3 without delay.
  - snps,dis-tx-ipgap-linecheck-quirk: when set, disable u2mac linestate check
 			during HS transmit.
+ - snps,parkmode-disable-ss-quirk: when set, all SuperSpeed bus instances in
+			park mode are disabled.
  - snps,dis_metastability_quirk: when set, disable metastability workaround.
 			CAUTION: use only if you are absolutely sure of it.
  - snps,is-utmi-l1-suspend: true when DWC3 asserts output signal

Documentation/driver-api/libata.rst

@@ -250,7 +250,7 @@ High-level taskfile hooks
 
 ::
 
-    void (*qc_prep) (struct ata_queued_cmd *qc);
+    enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc);
     int (*qc_issue) (struct ata_queued_cmd *qc);
 
 

Documentation/filesystems/affs.txt

@@ -93,13 +93,15 @@ The Amiga protection flags RWEDRWEDHSPARWED are handled as follows:
 
   - R maps to r for user, group and others. On directories, R implies x.
 
-  - If both W and D are allowed, w will be set.
+  - W maps to w.
 
   - E maps to x.
 
-  - H and P are always retained and ignored under Linux.
+  - D is ignored.
 
-  - A is always reset when a file is written to.
+  - H, S and P are always retained and ignored under Linux.
+
+  - A is cleared when a file is written to.
 
 User id and group id will be used unless set[gu]id are given as mount
 options. Since most of the Amiga file systems are single user systems
@@ -111,11 +113,13 @@ Linux -> Amiga:
 
 The Linux rwxrwxrwx file mode is handled as follows:
 
-  - r permission will set R for user, group and others.
+  - r permission will allow R for user, group and others.
 
-  - w permission will set W and D for user, group and others.
+  - w permission will allow W for user, group and others.
 
-  - x permission of the user will set E for plain files.
+  - x permission of the user will allow E for plain files.
+
+  - D will be allowed for user, group and others.
 
   - All other flags (suid, sgid, ...) are ignored and will
     not be retained.

Documentation/filesystems/seq_file.txt

@@ -192,6 +192,12 @@ between the calls to start() and stop(), so holding a lock during that time
 is a reasonable thing to do. The seq_file code will also avoid taking any
 other locks while the iterator is active.
 
+The iterater value returned by start() or next() is guaranteed to be
+passed to a subsequent next() or stop() call.  This allows resources
+such as locks that were taken to be reliably released.  There is *no*
+guarantee that the iterator will be passed to show(), though in practice
+it often will be.
+
 
 Formatted output
 

Documentation/filesystems/sysfs.txt

@@ -232,12 +232,10 @@ Other notes:
   is 4096. 
 
 - show() methods should return the number of bytes printed into the
-  buffer. This is the return value of scnprintf().
+  buffer.
 
-- show() must not use snprintf() when formatting the value to be
+- show() should only use sysfs_emit() or sysfs_emit_at() when formatting
-  returned to user space. If you can guarantee that an overflow
+  the value to be returned to user space.
-  will never happen you can use sprintf() otherwise you must use
-  scnprintf().
 
 - store() should return the number of bytes used from the buffer. If the
   entire buffer has been used, just return the count argument.

Documentation/index.rst

@@ -135,6 +135,14 @@ needed).
    mic/index
    scheduler/index
 
+Architecture-agnostic documentation
+-----------------------------------
+
+.. toctree::
+   :maxdepth: 2
+
+   asm-annotations
+
 Architecture-specific documentation
 -----------------------------------
 

Documentation/ioctl/ioctl-number.rst

@@ -321,6 +321,7 @@ Code  Seq#    Include File                                           Comments
                                                                      <mailto:tlewis@mindspring.com>
 0xA3  90-9F  linux/dtlk.h
 0xA4  00-1F  uapi/linux/tee.h                                        Generic TEE subsystem
+0xA4  00-1F  uapi/asm/sgx.h                                          <mailto:linux-sgx@vger.kernel.org>
 0xAA  00-3F  linux/uapi/linux/userfaultfd.h
 0xAB  00-1F  linux/nbd.h
 0xAC  00-1F  linux/raw.h

Documentation/kbuild/index.rst

@@ -19,6 +19,7 @@ Kernel Build System
 
     issues
     reproducible-builds
+    llvm
 
 .. only::  subproject and html
 

Documentation/kbuild/kbuild.rst

@@ -262,3 +262,8 @@ KBUILD_BUILD_USER, KBUILD_BUILD_HOST
 These two variables allow to override the user@host string displayed during
 boot and in /proc/version. The default value is the output of the commands
 whoami and host, respectively.
+
+LLVM
+----
+If this variable is set to 1, Kbuild will use Clang and LLVM utilities instead
+of GCC and GNU binutils to build the kernel.

Documentation/kbuild/llvm.rst

@@ -0,0 +1,87 @@
+==============================
+Building Linux with Clang/LLVM
+==============================
+
+This document covers how to build the Linux kernel with Clang and LLVM
+utilities.
+
+About
+-----
+
+The Linux kernel has always traditionally been compiled with GNU toolchains
+such as GCC and binutils. Ongoing work has allowed for `Clang
+<https://clang.llvm.org/>`_ and `LLVM <https://llvm.org/>`_ utilities to be
+used as viable substitutes. Distributions such as `Android
+<https://www.android.com/>`_, `ChromeOS
+<https://www.chromium.org/chromium-os>`_, and `OpenMandriva
+<https://www.openmandriva.org/>`_ use Clang built kernels.  `LLVM is a
+collection of toolchain components implemented in terms of C++ objects
+<https://www.aosabook.org/en/llvm.html>`_. Clang is a front-end to LLVM that
+supports C and the GNU C extensions required by the kernel, and is pronounced
+"klang," not "see-lang."
+
+Clang
+-----
+
+The compiler used can be swapped out via `CC=` command line argument to `make`.
+`CC=` should be set when selecting a config and during a build.
+
+	make CC=clang defconfig
+
+	make CC=clang
+
+Cross Compiling
+---------------
+
+A single Clang compiler binary will typically contain all supported backends,
+which can help simplify cross compiling.
+
+	ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang
+
+`CROSS_COMPILE` is not used to prefix the Clang compiler binary, instead
+`CROSS_COMPILE` is used to set a command line flag: `--target <triple>`. For
+example:
+
+	clang --target aarch64-linux-gnu foo.c
+
+LLVM Utilities
+--------------
+
+LLVM has substitutes for GNU binutils utilities. Kbuild supports `LLVM=1`
+to enable them.
+
+	make LLVM=1
+
+They can be enabled individually. The full list of the parameters:
+
+	make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \\
+	  OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \\
+	  READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \\
+	  HOSTLD=ld.lld
+
+Currently, the integrated assembler is disabled by default. You can pass
+`LLVM_IAS=1` to enable it.
+
+Getting Help
+------------
+
+- `Website <https://clangbuiltlinux.github.io/>`_
+- `Mailing List <https://groups.google.com/forum/#!forum/clang-built-linux>`_: <clang-built-linux@googlegroups.com>
+- `Issue Tracker <https://github.com/ClangBuiltLinux/linux/issues>`_
+- IRC: #clangbuiltlinux on chat.freenode.net
+- `Telegram <https://t.me/ClangBuiltLinux>`_: @ClangBuiltLinux
+- `Wiki <https://github.com/ClangBuiltLinux/linux/wiki>`_
+- `Beginner Bugs <https://github.com/ClangBuiltLinux/linux/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22>`_
+
+Getting LLVM
+-------------
+
+- http://releases.llvm.org/download.html
+- https://github.com/llvm/llvm-project
+- https://llvm.org/docs/GettingStarted.html
+- https://llvm.org/docs/CMake.html
+- https://apt.llvm.org/
+- https://www.archlinux.org/packages/extra/x86_64/llvm/
+- https://github.com/ClangBuiltLinux/tc-build
+- https://github.com/ClangBuiltLinux/linux/wiki/Building-Clang-from-source
+- https://android.googlesource.com/platform/prebuilts/clang/host/linux-x86/

Documentation/lzo.txt

@@ -159,11 +159,15 @@ Byte sequences
            distance = 16384 + (H << 14) + D
            state = S (copy S literals after this block)
            End of stream is reached if distance == 16384
+           In version 1 only, to prevent ambiguity with the RLE case when
+           ((distance & 0x803f) == 0x803f) && (261 <= length <= 264), the
+           compressor must not emit block copies where distance and length
+           meet these conditions.
 
         In version 1 only, this instruction is also used to encode a run of
-        zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
+           zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
            In this case, it is followed by a fourth byte, X.
-           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4.
+           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4
 
       0 0 1 L L L L L  (32..63)
            Copy of small block within 16kB distance (preferably less than 34B)

Documentation/media/uapi/v4l/colorspaces-defs.rst

@@ -36,8 +36,7 @@ whole range, 0-255, dividing the angular value by 1.41. The enum
 :c:type:`v4l2_hsv_encoding` specifies which encoding is used.
 
 .. note:: The default R'G'B' quantization is full range for all
-   colorspaces except for BT.2020 which uses limited range R'G'B'
+   colorspaces. HSV formats are always full range.
-   quantization.
 
 .. tabularcolumns:: |p{6.7cm}|p{10.8cm}|
 
@@ -169,8 +168,8 @@ whole range, 0-255, dividing the angular value by 1.41. The enum
       - Details
     * - ``V4L2_QUANTIZATION_DEFAULT``
       - Use the default quantization encoding as defined by the
-	colorspace. This is always full range for R'G'B' (except for the
+	colorspace. This is always full range for R'G'B' and HSV.
-	BT.2020 colorspace) and HSV. It is usually limited range for Y'CbCr.
+	It is usually limited range for Y'CbCr.
     * - ``V4L2_QUANTIZATION_FULL_RANGE``
       - Use the full range quantization encoding. I.e. the range [0…1] is
 	mapped to [0…255] (with possible clipping to [1…254] to avoid the
@@ -180,4 +179,4 @@ whole range, 0-255, dividing the angular value by 1.41. The enum
     * - ``V4L2_QUANTIZATION_LIM_RANGE``
       - Use the limited range quantization encoding. I.e. the range [0…1]
 	is mapped to [16…235]. Cb and Cr are mapped from [-0.5…0.5] to
-	[16…240].
+	[16…240]. Limited Range cannot be used with HSV.

Documentation/media/uapi/v4l/colorspaces-details.rst

@@ -377,9 +377,8 @@ Colorspace BT.2020 (V4L2_COLORSPACE_BT2020)
 The :ref:`itu2020` standard defines the colorspace used by Ultra-high
 definition television (UHDTV). The default transfer function is
 ``V4L2_XFER_FUNC_709``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_BT2020``. The default R'G'B' quantization is limited
+``V4L2_YCBCR_ENC_BT2020``. The default Y'CbCr quantization is limited range.
-range (!), and so is the default Y'CbCr quantization. The chromaticities
+The chromaticities of the primary colors and the white reference are:
-of the primary colors and the white reference are:
 
 
 

Documentation/networking/ip-sysctl.txt

@@ -750,6 +750,11 @@ tcp_tw_reuse - INTEGER
 	experts.
 	Default: 2
 
+tcp_tw_timeout - INTEGER
+	How long to wait to destroy TIME-WAIT state. The maximum value
+	is 60 seconds, the minimum value is 10 second.
+	Default: 60 seconds
+
 tcp_window_scaling - BOOLEAN
 	Enable window scaling as defined in RFC1323.
 
@@ -1008,12 +1013,14 @@ icmp_ratelimit - INTEGER
 icmp_msgs_per_sec - INTEGER
 	Limit maximal number of ICMP packets sent per second from this host.
 	Only messages whose type matches icmp_ratemask (see below) are
-	controlled by this limit.
+	controlled by this limit. For security reasons, the precise count
+	of messages per second is randomized.
 	Default: 1000
 
 icmp_msgs_burst - INTEGER
 	icmp_msgs_per_sec controls number of ICMP packets sent per second,
 	while icmp_msgs_burst controls the burst size of these packets.
+	For security reasons, the precise burst size is randomized.
 	Default: 50
 
 icmp_ratemask - INTEGER

Documentation/networking/j1939.rst

@@ -414,8 +414,8 @@ Send:
 		.can_family = AF_CAN,
 		.can_addr.j1939 = {
 			.name = J1939_NO_NAME;
-			.pgn = 0x30,
+			.addr = 0x30,
-			.addr = 0x12300,
+			.pgn = 0x12300,
 		},
 	};
 

Documentation/sound/hd-audio/index.rst

@@ -8,3 +8,4 @@ HD-Audio
    models
    controls
    dp-mst
+   realtek-pc-beep

Documentation/sound/hd-audio/models.rst

@@ -216,8 +216,6 @@ alc298-dell-aio
     ALC298 fixups on Dell AIO machines
 alc275-dell-xps
     ALC275 fixups on Dell XPS models
-alc256-dell-xps13
-    ALC256 fixups on Dell XPS13
 lenovo-spk-noise
     Workaround for speaker noise on Lenovo machines
 lenovo-hotkey

Documentation/sound/hd-audio/realtek-pc-beep.rst

@@ -0,0 +1,129 @@
+===============================
+Realtek PC Beep Hidden Register
+===============================
+
+This file documents the "PC Beep Hidden Register", which is present in certain
+Realtek HDA codecs and controls a muxer and pair of passthrough mixers that can
+route audio between pins but aren't themselves exposed as HDA widgets. As far
+as I can tell, these hidden routes are designed to allow flexible PC Beep output
+for codecs that don't have mixer widgets in their output paths. Why it's easier
+to hide a mixer behind an undocumented vendor register than to just expose it
+as a widget, I have no idea.
+
+Register Description
+====================
+
+The register is accessed via processing coefficient 0x36 on NID 20h. Bits not
+identified below have no discernible effect on my machine, a Dell XPS 13 9350::
+
+  MSB                           LSB
+  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+  | |h|S|L|         | B |R|       | Known bits
+  +=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+
+  |0|0|1|1|  0x7  |0|0x0|1|  0x7  | Reset value
+  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+1Ah input select (B): 2 bits
+  When zero, expose the PC Beep line (from the internal beep generator, when
+  enabled with the Set Beep Generation verb on NID 01h, or else from the
+  external PCBEEP pin) on the 1Ah pin node. When nonzero, expose the headphone
+  jack (or possibly Line In on some machines) input instead. If PC Beep is
+  selected, the 1Ah boost control has no effect.
+
+Amplify 1Ah loopback, left (L): 1 bit
+  Amplify the left channel of 1Ah before mixing it into outputs as specified
+  by h and S bits. Does not affect the level of 1Ah exposed to other widgets.
+
+Amplify 1Ah loopback, right (R): 1 bit
+  Amplify the right channel of 1Ah before mixing it into outputs as specified
+  by h and S bits. Does not affect the level of 1Ah exposed to other widgets.
+
+Loopback 1Ah to 21h [active low] (h): 1 bit
+  When zero, mix 1Ah (possibly with amplification, depending on L and R bits)
+  into 21h (headphone jack on my machine). Mixed signal respects the mute
+  setting on 21h.
+
+Loopback 1Ah to 14h (S): 1 bit
+  When one, mix 1Ah (possibly with amplification, depending on L and R bits)
+  into 14h (internal speaker on my machine). Mixed signal **ignores** the mute
+  setting on 14h and is present whenever 14h is configured as an output.
+
+Path diagrams
+=============
+
+1Ah input selection (DIV is the PC Beep divider set on NID 01h)::
+
+  <Beep generator>   <PCBEEP pin>    <Headphone jack>
+          |                |                |
+          +--DIV--+--!DIV--+       {1Ah boost control}
+                  |                         |
+                  +--(b == 0)--+--(b != 0)--+
+                               |
+               >1Ah (Beep/Headphone Mic/Line In)<
+
+Loopback of 1Ah to 21h/14h::
+
+               <1Ah (Beep/Headphone Mic/Line In)>
+                               |
+                        {amplify if L/R}
+                               |
+                  +-----!h-----+-----S-----+
+                  |                        |
+          {21h mute control}               |
+                  |                        |
+          >21h (Headphone)<     >14h (Internal Speaker)<
+
+Background
+==========
+
+All Realtek HDA codecs have a vendor-defined widget with node ID 20h which
+provides access to a bank of registers that control various codec functions.
+Registers are read and written via the standard HDA processing coefficient
+verbs (Set/Get Coefficient Index, Set/Get Processing Coefficient). The node is
+named "Realtek Vendor Registers" in public datasheets' verb listings and,
+apart from that, is entirely undocumented.
+
+This particular register, exposed at coefficient 0x36 and named in commits from
+Realtek, is of note: unlike most registers, which seem to control detailed
+amplifier parameters not in scope of the HDA specification, it controls audio
+routing which could just as easily have been defined using standard HDA mixer
+and selector widgets.
+
+Specifically, it selects between two sources for the input pin widget with Node
+ID (NID) 1Ah: the widget's signal can come either from an audio jack (on my
+laptop, a Dell XPS 13 9350, it's the headphone jack, but comments in Realtek
+commits indicate that it might be a Line In on some machines) or from the PC
+Beep line (which is itself multiplexed between the codec's internal beep
+generator and external PCBEEP pin, depending on if the beep generator is
+enabled via verbs on NID 01h). Additionally, it can mix (with optional
+amplification) that signal onto the 21h and/or 14h output pins.
+
+The register's reset value is 0x3717, corresponding to PC Beep on 1Ah that is
+then amplified and mixed into both the headphones and the speakers. Not only
+does this violate the HDA specification, which says that "[a vendor defined
+beep input pin] connection may be maintained *only* while the Link reset
+(**RST#**) is asserted", it means that we cannot ignore the register if we care
+about the input that 1Ah would otherwise expose or if the PCBEEP trace is
+poorly shielded and picks up chassis noise (both of which are the case on my
+machine).
+
+Unfortunately, there are lots of ways to get this register configuration wrong.
+Linux, it seems, has gone through most of them. For one, the register resets
+after S3 suspend: judging by existing code, this isn't the case for all vendor
+registers, and it's led to some fixes that improve behavior on cold boot but
+don't last after suspend. Other fixes have successfully switched the 1Ah input
+away from PC Beep but have failed to disable both loopback paths. On my
+machine, this means that the headphone input is amplified and looped back to
+the headphone output, which uses the exact same pins! As you might expect, this
+causes terrible headphone noise, the character of which is controlled by the
+1Ah boost control. (If you've seen instructions online to fix XPS 13 headphone
+noise by changing "Headphone Mic Boost" in ALSA, now you know why.)
+
+The information here has been obtained through black-box reverse engineering of
+the ALC256 codec's behavior and is not guaranteed to be correct. It likely
+also applies for the ALC255, ALC257, ALC235, and ALC236, since those codecs
+seem to be close relatives of the ALC256. (They all share one initialization
+function.) Additionally, other codecs like the ALC225 and ALC285 also have this
+register, judging by existing fixups in ``patch_realtek.c``, but specific
+data (e.g. node IDs, bit positions, pin mappings) for those codecs may differ
+from what I've described here.

Documentation/virt/kvm/api.txt

@@ -172,6 +172,9 @@ is dependent on the CPU capability and the kernel configuration. The limit can
 be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
 ioctl() at run-time.
 
+Creation of the VM will fail if the requested IPA size (whether it is
+implicit or explicit) is unsupported on the host.
+
 Please note that configuring the IPA size does not affect the capability
 exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
 size of the address translated by the stage2 level (guest physical to
@@ -1132,6 +1135,9 @@ field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including
 anonymous memory, ordinary files, and hugetlbfs.
 
+On architectures that support a form of address tagging, userspace_addr must
+be an untagged address.
+
 It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
 be identical.  This allows large pages in the guest to be backed by large
 pages in the host.
@@ -4444,9 +4450,11 @@ EOI was received.
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
 			__u32 type;
+			__u32 pad1;
 			union {
 				struct {
 					__u32 msr;
+					__u32 pad2;
 					__u64 control;
 					__u64 evt_page;
 					__u64 msg_page;

Documentation/virt/kvm/mmu.txt

@@ -420,7 +420,7 @@ If the generation number of the spte does not equal the global generation
 number, it will ignore the cached MMIO information and handle the page
 fault through the slow path.
 
-Since only 19 bits are used to store generation-number on mmio spte, all
+Since only 18 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
 Unfortunately, a single memory access might access kvm_memslots(kvm) multiple

Documentation/x86/index.rst

@@ -31,3 +31,4 @@ x86-specific Documentation
    usb-legacy-support
    i386/index
    x86_64/index
+   sgx

Documentation/x86/sgx.rst

@@ -0,0 +1,211 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================
+Software Guard eXtensions (SGX)
+===============================
+
+Overview
+========
+
+Software Guard eXtensions (SGX) hardware enables for user space applications
+to set aside private memory regions of code and data:
+
+* Privileged (ring-0) ENCLS functions orchestrate the construction of the.
+  regions.
+* Unprivileged (ring-3) ENCLU functions allow an application to enter and
+  execute inside the regions.
+
+These memory regions are called enclaves. An enclave can be only entered at a
+fixed set of entry points. Each entry point can hold a single hardware thread
+at a time.  While the enclave is loaded from a regular binary file by using
+ENCLS functions, only the threads inside the enclave can access its memory. The
+region is denied from outside access by the CPU, and encrypted before it leaves
+from LLC.
+
+The support can be determined by
+
+	``grep sgx /proc/cpuinfo``
+
+SGX must both be supported in the processor and enabled by the BIOS.  If SGX
+appears to be unsupported on a system which has hardware support, ensure
+support is enabled in the BIOS.  If a BIOS presents a choice between "Enabled"
+and "Software Enabled" modes for SGX, choose "Enabled".
+
+Enclave Page Cache
+==================
+
+SGX utilizes an *Enclave Page Cache (EPC)* to store pages that are associated
+with an enclave. It is contained in a BIOS-reserved region of physical memory.
+Unlike pages used for regular memory, pages can only be accessed from outside of
+the enclave during enclave construction with special, limited SGX instructions.
+
+Only a CPU executing inside an enclave can directly access enclave memory.
+However, a CPU executing inside an enclave may access normal memory outside the
+enclave.
+
+The kernel manages enclave memory similar to how it treats device memory.
+
+Enclave Page Types
+------------------
+
+**SGX Enclave Control Structure (SECS)**
+   Enclave's address range, attributes and other global data are defined
+   by this structure.
+
+**Regular (REG)**
+   Regular EPC pages contain the code and data of an enclave.
+
+**Thread Control Structure (TCS)**
+   Thread Control Structure pages define the entry points to an enclave and
+   track the execution state of an enclave thread.
+
+**Version Array (VA)**
+   Version Array pages contain 512 slots, each of which can contain a version
+   number for a page evicted from the EPC.
+
+Enclave Page Cache Map
+----------------------
+
+The processor tracks EPC pages in a hardware metadata structure called the
+*Enclave Page Cache Map (EPCM)*.  The EPCM contains an entry for each EPC page
+which describes the owning enclave, access rights and page type among the other
+things.
+
+EPCM permissions are separate from the normal page tables.  This prevents the
+kernel from, for instance, allowing writes to data which an enclave wishes to
+remain read-only.  EPCM permissions may only impose additional restrictions on
+top of normal x86 page permissions.
+
+For all intents and purposes, the SGX architecture allows the processor to
+invalidate all EPCM entries at will.  This requires that software be prepared to
+handle an EPCM fault at any time.  In practice, this can happen on events like
+power transitions when the ephemeral key that encrypts enclave memory is lost.
+
+Application interface
+=====================
+
+Enclave build functions
+-----------------------
+
+In addition to the traditional compiler and linker build process, SGX has a
+separate enclave “build” process.  Enclaves must be built before they can be
+executed (entered). The first step in building an enclave is opening the
+**/dev/sgx_enclave** device.  Since enclave memory is protected from direct
+access, special privileged instructions are Then used to copy data into enclave
+pages and establish enclave page permissions.
+
+.. kernel-doc:: arch/x86/kernel/cpu/sgx/ioctl.c
+   :functions: sgx_ioc_enclave_create
+               sgx_ioc_enclave_add_pages
+               sgx_ioc_enclave_init
+               sgx_ioc_enclave_provision
+
+Enclave vDSO
+------------
+
+Entering an enclave can only be done through SGX-specific EENTER and ERESUME
+functions, and is a non-trivial process.  Because of the complexity of
+transitioning to and from an enclave, enclaves typically utilize a library to
+handle the actual transitions.  This is roughly analogous to how glibc
+implementations are used by most applications to wrap system calls.
+
+Another crucial characteristic of enclaves is that they can generate exceptions
+as part of their normal operation that need to be handled in the enclave or are
+unique to SGX.
+
+Instead of the traditional signal mechanism to handle these exceptions, SGX
+can leverage special exception fixup provided by the vDSO.  The kernel-provided
+vDSO function wraps low-level transitions to/from the enclave like EENTER and
+ERESUME.  The vDSO function intercepts exceptions that would otherwise generate
+a signal and return the fault information directly to its caller.  This avoids
+the need to juggle signal handlers.
+
+.. kernel-doc:: arch/x86/include/uapi/asm/sgx.h
+   :functions: vdso_sgx_enter_enclave_t
+
+ksgxd
+=====
+
+SGX support includes a kernel thread called *ksgxwapd*.
+
+EPC sanitization
+----------------
+
+ksgxd is started when SGX initializes.  Enclave memory is typically ready
+For use when the processor powers on or resets.  However, if SGX has been in
+use since the reset, enclave pages may be in an inconsistent state.  This might
+occur after a crash and kexec() cycle, for instance.  At boot, ksgxd
+reinitializes all enclave pages so that they can be allocated and re-used.
+
+The sanitization is done by going through EPC address space and applying the
+EREMOVE function to each physical page. Some enclave pages like SECS pages have
+hardware dependencies on other pages which prevents EREMOVE from functioning.
+Executing two EREMOVE passes removes the dependencies.
+
+Page reclaimer
+--------------
+
+Similar to the core kswapd, ksgxd, is responsible for managing the
+overcommitment of enclave memory.  If the system runs out of enclave memory,
+*ksgxwapd* “swaps” enclave memory to normal memory.
+
+Launch Control
+==============
+
+SGX provides a launch control mechanism. After all enclave pages have been
+copied, kernel executes EINIT function, which initializes the enclave. Only after
+this the CPU can execute inside the enclave.
+
+ENIT function takes an RSA-3072 signature of the enclave measurement.  The function
+checks that the measurement is correct and signature is signed with the key
+hashed to the four **IA32_SGXLEPUBKEYHASH{0, 1, 2, 3}** MSRs representing the
+SHA256 of a public key.
+
+Those MSRs can be configured by the BIOS to be either readable or writable.
+Linux supports only writable configuration in order to give full control to the
+kernel on launch control policy. Before calling EINIT function, the driver sets
+the MSRs to match the enclave's signing key.
+
+Encryption engines
+==================
+
+In order to conceal the enclave data while it is out of the CPU package, the
+memory controller has an encryption engine to transparently encrypt and decrypt
+enclave memory.
+
+In CPUs prior to Ice Lake, the Memory Encryption Engine (MEE) is used to
+encrypt pages leaving the CPU caches. MEE uses a n-ary Merkle tree with root in
+SRAM to maintain integrity of the encrypted data. This provides integrity and
+anti-replay protection but does not scale to large memory sizes because the time
+required to update the Merkle tree grows logarithmically in relation to the
+memory size.
+
+CPUs starting from Icelake use Total Memory Encryption (TME) in the place of
+MEE. TME-based SGX implementations do not have an integrity Merkle tree, which
+means integrity and replay-attacks are not mitigated.  B, it includes
+additional changes to prevent cipher text from being returned and SW memory
+aliases from being Created.
+
+DMA to enclave memory is blocked by range registers on both MEE and TME systems
+(SDM section 41.10).
+
+Usage Models
+============
+
+Shared Library
+--------------
+
+Sensitive data and the code that acts on it is partitioned from the application
+into a separate library. The library is then linked as a DSO which can be loaded
+into an enclave. The application can then make individual function calls into
+the enclave through special SGX instructions. A run-time within the enclave is
+configured to marshal function parameters into and out of the enclave and to
+call the correct library function.
+
+Application Container
+---------------------
+
+An application may be loaded into a container enclave which is specially
+configured with a library OS and run-time which permits the application to run.
+The enclave run-time and library OS work together to execute the application
+when a thread enters the enclave.

Documentation/x86/topology.rst

@@ -41,6 +41,8 @@ Package
 Packages contain a number of cores plus shared resources, e.g. DRAM
 controller, shared caches etc.
 
+Modern systems may also use the term 'Die' for package.
+
 AMD nomenclature for package is 'Node'.
 
 Package-related topology information in the kernel:
@@ -53,11 +55,18 @@ Package-related topology information in the kernel:
 
     The number of dies in a package. This information is retrieved via CPUID.
 
+  - cpuinfo_x86.cpu_die_id:
+
+    The physical ID of the die. This information is retrieved via CPUID.
+
   - cpuinfo_x86.phys_proc_id:
 
     The physical ID of the package. This information is retrieved via CPUID
     and deduced from the APIC IDs of the cores in the package.
 
+    Modern systems use this value for the socket. There may be multiple
+    packages within a socket. This value may differ from cpu_die_id.
+
   - cpuinfo_x86.logical_proc_id:
 
     The logical ID of the package. As we do not trust BIOSes to enumerate the

Documentation/x86/x86_64/fsgs.rst

@@ -0,0 +1,199 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Using FS and GS segments in user space applications
+===================================================
+
+The x86 architecture supports segmentation. Instructions which access
+memory can use segment register based addressing mode. The following
+notation is used to address a byte within a segment:
+
+  Segment-register:Byte-address
+
+The segment base address is added to the Byte-address to compute the
+resulting virtual address which is accessed. This allows to access multiple
+instances of data with the identical Byte-address, i.e. the same code. The
+selection of a particular instance is purely based on the base-address in
+the segment register.
+
+In 32-bit mode the CPU provides 6 segments, which also support segment
+limits. The limits can be used to enforce address space protections.
+
+In 64-bit mode the CS/SS/DS/ES segments are ignored and the base address is
+always 0 to provide a full 64bit address space. The FS and GS segments are
+still functional in 64-bit mode.
+
+Common FS and GS usage
+------------------------------
+
+The FS segment is commonly used to address Thread Local Storage (TLS). FS
+is usually managed by runtime code or a threading library. Variables
+declared with the '__thread' storage class specifier are instantiated per
+thread and the compiler emits the FS: address prefix for accesses to these
+variables. Each thread has its own FS base address so common code can be
+used without complex address offset calculations to access the per thread
+instances. Applications should not use FS for other purposes when they use
+runtimes or threading libraries which manage the per thread FS.
+
+The GS segment has no common use and can be used freely by
+applications. GCC and Clang support GS based addressing via address space
+identifiers.
+
+Reading and writing the FS/GS base address
+------------------------------------------
+
+There exist two mechanisms to read and write the FS/GS base address:
+
+ - the arch_prctl() system call
+
+ - the FSGSBASE instruction family
+
+Accessing FS/GS base with arch_prctl()
+--------------------------------------
+
+ The arch_prctl(2) based mechanism is available on all 64-bit CPUs and all
+ kernel versions.
+
+ Reading the base:
+
+   arch_prctl(ARCH_GET_FS, &fsbase);
+   arch_prctl(ARCH_GET_GS, &gsbase);
+
+ Writing the base:
+
+   arch_prctl(ARCH_SET_FS, fsbase);
+   arch_prctl(ARCH_SET_GS, gsbase);
+
+ The ARCH_SET_GS prctl may be disabled depending on kernel configuration
+ and security settings.
+
+Accessing FS/GS base with the FSGSBASE instructions
+---------------------------------------------------
+
+ With the Ivy Bridge CPU generation Intel introduced a new set of
+ instructions to access the FS and GS base registers directly from user
+ space. These instructions are also supported on AMD Family 17H CPUs. The
+ following instructions are available:
+
+  =============== ===========================
+  RDFSBASE %reg   Read the FS base register
+  RDGSBASE %reg   Read the GS base register
+  WRFSBASE %reg   Write the FS base register
+  WRGSBASE %reg   Write the GS base register
+  =============== ===========================
+
+ The instructions avoid the overhead of the arch_prctl() syscall and allow
+ more flexible usage of the FS/GS addressing modes in user space
+ applications. This does not prevent conflicts between threading libraries
+ and runtimes which utilize FS and applications which want to use it for
+ their own purpose.
+
+FSGSBASE instructions enablement
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ The instructions are enumerated in CPUID leaf 7, bit 0 of EBX. If
+ available /proc/cpuinfo shows 'fsgsbase' in the flag entry of the CPUs.
+
+ The availability of the instructions does not enable them
+ automatically. The kernel has to enable them explicitly in CR4. The
+ reason for this is that older kernels make assumptions about the values in
+ the GS register and enforce them when GS base is set via
+ arch_prctl(). Allowing user space to write arbitrary values to GS base
+ would violate these assumptions and cause malfunction.
+
+ On kernels which do not enable FSGSBASE the execution of the FSGSBASE
+ instructions will fault with a #UD exception.
+
+ The kernel provides reliable information about the enabled state in the
+ ELF AUX vector. If the HWCAP2_FSGSBASE bit is set in the AUX vector, the
+ kernel has FSGSBASE instructions enabled and applications can use them.
+ The following code example shows how this detection works::
+
+   #include <sys/auxv.h>
+   #include <elf.h>
+
+   /* Will be eventually in asm/hwcap.h */
+   #ifndef HWCAP2_FSGSBASE
+   #define HWCAP2_FSGSBASE        (1 << 1)
+   #endif
+
+   ....
+
+   unsigned val = getauxval(AT_HWCAP2);
+
+   if (val & HWCAP2_FSGSBASE)
+        printf("FSGSBASE enabled\n");
+
+FSGSBASE instructions compiler support
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+GCC version 4.6.4 and newer provide instrinsics for the FSGSBASE
+instructions. Clang 5 supports them as well.
+
+  =================== ===========================
+  _readfsbase_u64()   Read the FS base register
+  _readfsbase_u64()   Read the GS base register
+  _writefsbase_u64()  Write the FS base register
+  _writegsbase_u64()  Write the GS base register
+  =================== ===========================
+
+To utilize these instrinsics <immintrin.h> must be included in the source
+code and the compiler option -mfsgsbase has to be added.
+
+Compiler support for FS/GS based addressing
+-------------------------------------------
+
+GCC version 6 and newer provide support for FS/GS based addressing via
+Named Address Spaces. GCC implements the following address space
+identifiers for x86:
+
+  ========= ====================================
+  __seg_fs  Variable is addressed relative to FS
+  __seg_gs  Variable is addressed relative to GS
+  ========= ====================================
+
+The preprocessor symbols __SEG_FS and __SEG_GS are defined when these
+address spaces are supported. Code which implements fallback modes should
+check whether these symbols are defined. Usage example::
+
+  #ifdef __SEG_GS
+
+  long data0 = 0;
+  long data1 = 1;
+
+  long __seg_gs *ptr;
+
+  /* Check whether FSGSBASE is enabled by the kernel (HWCAP2_FSGSBASE) */
+  ....
+
+  /* Set GS base to point to data0 */
+  _writegsbase_u64(&data0);
+
+  /* Access offset 0 of GS */
+  ptr = 0;
+  printf("data0 = %ld\n", *ptr);
+
+  /* Set GS base to point to data1 */
+  _writegsbase_u64(&data1);
+  /* ptr still addresses offset 0! */
+  printf("data1 = %ld\n", *ptr);
+
+
+Clang does not provide the GCC address space identifiers, but it provides
+address spaces via an attribute based mechanism in Clang 2.6 and newer
+versions:
+
+ ==================================== =====================================
+  __attribute__((address_space(256))  Variable is addressed relative to GS
+  __attribute__((address_space(257))  Variable is addressed relative to FS
+ ==================================== =====================================
+
+FS/GS based addressing with inline assembly
+-------------------------------------------
+
+In case the compiler does not support address spaces, inline assembly can
+be used for FS/GS based addressing mode::
+
+	mov %fs:offset, %reg
+	mov %gs:offset, %reg
+
+	mov %reg, %fs:offset
+	mov %reg, %gs:offset

Documentation/x86/x86_64/index.rst

@@ -14,3 +14,4 @@ x86_64 Support
    fake-numa-for-cpusets
    cpu-hotplug-spec
    machinecheck
+   fsgs

Documentation/xtensa/mmu.rst

@@ -82,7 +82,8 @@ Default MMUv2-compatible layout::
   +------------------+
   | VMALLOC area     |  VMALLOC_START            0xc0000000  128MB - 64KB
   +------------------+  VMALLOC_END
-  | Cache aliasing   |  TLBTEMP_BASE_1           0xc7ff0000  DCACHE_WAY_SIZE
+  +------------------+
+  | Cache aliasing   |  TLBTEMP_BASE_1           0xc8000000  DCACHE_WAY_SIZE
   | remap area 1     |
   +------------------+
   | Cache aliasing   |  TLBTEMP_BASE_2                       DCACHE_WAY_SIZE
@@ -124,7 +125,8 @@ Default MMUv2-compatible layout::
   +------------------+
   | VMALLOC area     |  VMALLOC_START            0xa0000000  128MB - 64KB
   +------------------+  VMALLOC_END
-  | Cache aliasing   |  TLBTEMP_BASE_1           0xa7ff0000  DCACHE_WAY_SIZE
+  +------------------+
+  | Cache aliasing   |  TLBTEMP_BASE_1           0xa8000000  DCACHE_WAY_SIZE
   | remap area 1     |
   +------------------+
   | Cache aliasing   |  TLBTEMP_BASE_2                       DCACHE_WAY_SIZE
@@ -167,7 +169,8 @@ Default MMUv2-compatible layout::
   +------------------+
   | VMALLOC area     |  VMALLOC_START            0x90000000  128MB - 64KB
   +------------------+  VMALLOC_END
-  | Cache aliasing   |  TLBTEMP_BASE_1           0x97ff0000  DCACHE_WAY_SIZE
+  +------------------+
+  | Cache aliasing   |  TLBTEMP_BASE_1           0x98000000  DCACHE_WAY_SIZE
   | remap area 1     |
   +------------------+
   | Cache aliasing   |  TLBTEMP_BASE_2                       DCACHE_WAY_SIZE

MAINTAINERS

@@ -3054,6 +3054,7 @@ R:	Martin KaFai Lau <kafai@fb.com>
 R:	Song Liu <songliubraving@fb.com>
 R:	Yonghong Song <yhs@fb.com>
 R:	Andrii Nakryiko <andriin@fb.com>
+R:	KP Singh <kpsingh@chromium.org>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
@@ -4028,6 +4029,7 @@ B:	https://github.com/ClangBuiltLinux/linux/issues
 C:	irc://chat.freenode.net/clangbuiltlinux
 S:	Supported
 K:	\b(?i:clang|llvm)\b
+F:	Documentation/kbuild/llvm.rst
 
 CLEANCACHE API
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
@@ -8516,6 +8518,19 @@ F:	Documentation/x86/intel_txt.rst
 F:	include/linux/tboot.h
 F:	arch/x86/kernel/tboot.c
 
+INTEL SGX
+M:	Jarkko Sakkinen <jarkko@kernel.org>
+L:	linux-sgx@vger.kernel.org
+S:	Supported
+Q:	https://patchwork.kernel.org/project/intel-sgx/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-sgx.git
+F:	Documentation/x86/sgx.rst
+F:	arch/x86/entry/vdso/vsgx.S
+F:	arch/x86/include/uapi/asm/sgx.h
+F:	arch/x86/kernel/cpu/sgx/*
+F:	tools/testing/selftests/sgx/*
+K:	\bSGX_
+
 INTERCONNECT API
 M:	Georgi Djakov <georgi.djakov@linaro.org>
 L:	linux-pm@vger.kernel.org
@@ -9144,6 +9159,7 @@ F:	include/linux/skmsg.h
 F:	net/core/skmsg.c
 F:	net/core/sock_map.c
 F:	net/ipv4/tcp_bpf.c
+F:	net/ipv4/udp_bpf.c
 
 LANTIQ / INTEL Ethernet drivers
 M:	Hauke Mehrtens <hauke@hauke-m.de>

Makefile

@@ -1,8 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# dist_make: Tencent Dist Makefile, which contains dist-* make targets
+ifneq ($(shell echo $(MAKECMDGOALS) | grep "^dist-"),)
+include dist/Makefile
+else
+
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 32
+SUBLEVEL = 119
-EXTRAVERSION = -1
+EXTRAVERSION = -20
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -394,8 +401,13 @@ HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS 2>/dev/null)
 HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null)
 HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null)
 
-HOSTCC       = gcc
+ifneq ($(LLVM),)
-HOSTCXX      = g++
+HOSTCC	= clang
+HOSTCXX	= clang++
+else
+HOSTCC	= gcc
+HOSTCXX	= g++
+endif
 KBUILD_HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
 		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS) \
 		$(HOSTCFLAGS)
@@ -404,28 +416,46 @@ KBUILD_HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS)
 KBUILD_HOSTLDLIBS   := $(HOST_LFS_LIBS) $(HOSTLDLIBS)
 
 # Make variables (CC, etc...)
-AS		= $(CROSS_COMPILE)as
-LD		= $(CROSS_COMPILE)ld
-CC		= $(CROSS_COMPILE)gcc
 CPP		= $(CC) -E
+ifneq ($(LLVM),)
+CC		= clang
+LD		= ld.lld
+AR		= llvm-ar
+NM		= llvm-nm
+OBJCOPY		= llvm-objcopy
+OBJDUMP		= llvm-objdump
+READELF		= llvm-readelf
+OBJSIZE		= llvm-size
+STRIP		= llvm-strip
+else
+CC		= $(CROSS_COMPILE)gcc
+LD		= $(CROSS_COMPILE)ld
 AR		= $(CROSS_COMPILE)ar
 NM		= $(CROSS_COMPILE)nm
-STRIP		= $(CROSS_COMPILE)strip
 OBJCOPY		= $(CROSS_COMPILE)objcopy
 OBJDUMP		= $(CROSS_COMPILE)objdump
+READELF		= $(CROSS_COMPILE)readelf
 OBJSIZE		= $(CROSS_COMPILE)size
+STRIP		= $(CROSS_COMPILE)strip
+endif
 PAHOLE		= pahole
+RESOLVE_BTFIDS	= $(objtree)/tools/bpf/resolve_btfids/resolve_btfids
 LEX		= flex
 YACC		= bison
 AWK		= awk
 INSTALLKERNEL  := installkernel
-DEPMOD		= /sbin/depmod
+DEPMOD		= depmod
 PERL		= perl
 PYTHON		= python
-PYTHON2		= python2
 PYTHON3		= python3
 CHECK		= sparse
 BASH		= bash
+KGZIP		= gzip
+KBZIP2		= bzip2
+KLZOP		= lzop
+LZMA		= lzma
+LZ4		= lz4c
+XZ		= xz
 
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF)
@@ -458,7 +488,7 @@ KBUILD_AFLAGS   := -D__ASSEMBLY__ -fno-PIE
 KBUILD_CFLAGS   := -Wall -Wundef -Werror=strict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common -fshort-wchar -fno-PIE \
 		   -Werror=implicit-function-declaration -Werror=implicit-int \
-		   -Wno-format-security \
+		   -Werror=return-type -Wno-format-security \
 		   -std=gnu89
 KBUILD_CPPFLAGS := -D__KERNEL__
 KBUILD_AFLAGS_KERNEL :=
@@ -471,9 +501,10 @@ KBUILD_LDFLAGS :=
 GCC_PLUGINS_CFLAGS :=
 CLANG_FLAGS :=
 
-export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
+export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE PAHOLE LEX YACC AWK INSTALLKERNEL
+export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
-export PERL PYTHON PYTHON2 PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
+export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
+export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ
 export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS
@@ -528,13 +559,13 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
 ifneq ($(CROSS_COMPILE),)
 CLANG_FLAGS	+= --target=$(notdir $(CROSS_COMPILE:%-=%))
 GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
-CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)
+CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
 GCC_TOOLCHAIN	:= $(realpath $(GCC_TOOLCHAIN_DIR)/..)
 endif
 ifneq ($(GCC_TOOLCHAIN),)
 CLANG_FLAGS	+= --gcc-toolchain=$(GCC_TOOLCHAIN)
 endif
-ifeq ($(shell $(AS) --version 2>&1 | head -n 1 | grep clang),)
+ifneq ($(LLVM_IAS),1)
 CLANG_FLAGS	+= -no-integrated-as
 endif
 CLANG_FLAGS	+= -Werror=unknown-warning-option
@@ -587,12 +618,8 @@ KBUILD_MODULES :=
 KBUILD_BUILTIN := 1
 
 # If we have only "make modules", don't compile built-in objects.
-# When we're building modules with modversions, we need to consider
-# the built-in objects during the descend as well, in order to
-# make sure the checksums are up to date before we record them.
-
 ifeq ($(MAKECMDGOALS),modules)
-  KBUILD_BUILTIN := $(if $(CONFIG_MODVERSIONS),1)
+  KBUILD_BUILTIN :=
 endif
 
 # If we have "make <whatever> modules", compile modules
@@ -707,12 +734,9 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS += -Os
 endif
 
-ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED
-KBUILD_CFLAGS   += -Wno-maybe-uninitialized
-endif
-
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
+KBUILD_CFLAGS	+= $(call cc-option,-fno-allow-store-data-races)
 
 include scripts/Makefile.kcov
 include scripts/Makefile.gcc-plugins
@@ -749,17 +773,20 @@ KBUILD_CFLAGS += -Wno-tautological-compare
 KBUILD_CFLAGS += -mno-global-merge
 else
 
-# These warnings generated too much noise in a regular build.
-# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
-KBUILD_CFLAGS += -Wno-unused-but-set-variable
-
 # Warn about unmarked fall-throughs in switch statement.
 # Disabled for clang while comment to attribute conversion happens and
 # https://github.com/ClangBuiltLinux/linux/issues/636 is discussed.
 KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough,)
 endif
 
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
 KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
+
+# These result in bogus false positives
+KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer)
+
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
@@ -786,8 +813,11 @@ DEBUG_CFLAGS	+= -gsplit-dwarf
 else
 DEBUG_CFLAGS	+= -g
 endif
+ifneq ($(LLVM_IAS),1)
 KBUILD_AFLAGS	+= -Wa,-gdwarf-2
 endif
+endif
+
 ifdef CONFIG_DEBUG_INFO_DWARF4
 DEBUG_CFLAGS	+= -gdwarf-4
 endif
@@ -860,6 +890,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 # disable stringop warnings in gcc 8+
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
+# We'll want to enable this eventually, but it's not going away for 5.7 at least
+KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
+
+# Another good warning that we'll want to enable eventually
+KBUILD_CFLAGS += $(call cc-disable-warning, restrict)
+
+# Enabled with W=2, disabled by default as noisy
+KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
@@ -890,12 +931,6 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=designated-init)
 # change __FILE__ to the relative path from the srctree
 KBUILD_CFLAGS	+= $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 
-# ensure -fcf-protection is disabled when using retpoline as it is
-# incompatible with -mindirect-branch=thunk-extern
-ifdef CONFIG_RETPOLINE
-KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
-endif
-
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 include scripts/Makefile.ubsan
@@ -977,10 +1012,10 @@ export mod_strip_cmd
 mod_compress_cmd = true
 ifdef CONFIG_MODULE_COMPRESS
   ifdef CONFIG_MODULE_COMPRESS_GZIP
-    mod_compress_cmd = gzip -n -f
+    mod_compress_cmd = $(KGZIP) -n -f
   endif # CONFIG_MODULE_COMPRESS_GZIP
   ifdef CONFIG_MODULE_COMPRESS_XZ
-    mod_compress_cmd = xz -f
+    mod_compress_cmd = $(XZ) -f
   endif # CONFIG_MODULE_COMPRESS_XZ
 endif # CONFIG_MODULE_COMPRESS
 export mod_compress_cmd
@@ -996,9 +1031,10 @@ export mod_sign_cmd
 
 HOST_LIBELF_LIBS = $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
 
+has_libelf = $(call try-run,\
+               echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0)
+
 ifdef CONFIG_STACK_VALIDATION
-  has_libelf := $(call try-run,\
-		echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0)
   ifeq ($(has_libelf),1)
     objtool_target := tools/objtool FORCE
   else
@@ -1007,6 +1043,14 @@ ifdef CONFIG_STACK_VALIDATION
   endif
 endif
 
+ifdef CONFIG_DEBUG_INFO_BTF
+  ifeq ($(has_libelf),1)
+    resolve_btfids_target := tools/bpf/resolve_btfids FORCE
+  else
+    ERROR_RESOLVE_BTFIDS := 1
+  endif
+endif
+
 PHONY += prepare0
 
 export MODORDER := $(extmod-prefix)modules.order
@@ -1111,7 +1155,7 @@ prepare0: archprepare
 	$(Q)$(MAKE) $(build)=.
 
 # All the preparing..
-prepare: prepare0 prepare-objtool
+prepare: prepare0 prepare-objtool prepare-resolve_btfids
 
 # Support for using generic headers in asm-generic
 asm-generic := -f $(srctree)/scripts/Makefile.asm-generic obj
@@ -1124,7 +1168,7 @@ uapi-asm-generic:
 	$(Q)$(MAKE) $(asm-generic)=arch/$(SRCARCH)/include/generated/uapi/asm \
 	generic=include/uapi/asm-generic
 
-PHONY += prepare-objtool
+PHONY += prepare-objtool prepare-resolve_btfids
 prepare-objtool: $(objtool_target)
 ifeq ($(SKIP_STACK_VALIDATION),1)
 ifdef CONFIG_UNWINDER_ORC
@@ -1135,6 +1179,11 @@ else
 endif
 endif
 
+prepare-resolve_btfids: $(resolve_btfids_target)
+ifeq ($(ERROR_RESOLVE_BTFIDS),1)
+	@echo "error: Cannot resolve BTF IDs for CONFIG_DEBUG_INFO_BTF, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2
+	@false
+endif
 # Generate some files
 # ---------------------------------------------------------------------------
 
@@ -1151,11 +1200,19 @@ define filechk_utsrelease.h
 endef
 
 define filechk_version.h
-	echo \#define LINUX_VERSION_CODE $(shell                         \
+	if [ $(SUBLEVEL) -gt 255 ]; then                                 \
-	expr $(VERSION) \* 65536 + 0$(PATCHLEVEL) \* 256 + 0$(SUBLEVEL)); \
+		echo \#define LINUX_VERSION_CODE $(shell                 \
-	echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))'
+		expr $(VERSION) \* 65536 + $(PATCHLEVEL) \* 256 + 255); \
+	else                                                             \
+		echo \#define LINUX_VERSION_CODE $(shell                 \
+		expr $(VERSION) \* 65536 + $(PATCHLEVEL) \* 256 + $(SUBLEVEL)); \
+	fi;                                                              \
+	echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) +  \
+	((c) > 255 ? 255 : (c)))'
 endef
 
+$(version_h): PATCHLEVEL := $(if $(PATCHLEVEL), $(PATCHLEVEL), 0)
+$(version_h): SUBLEVEL := $(if $(SUBLEVEL), $(SUBLEVEL), 0)
 $(version_h): FORCE
 	$(call filechk,version.h)
 	$(Q)rm -f $(old_version_h)
@@ -1238,11 +1295,15 @@ ifneq ($(dtstree),)
 	$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
 
 PHONY += dtbs dtbs_install dtbs_check
-dtbs dtbs_check: include/config/kernel.release scripts_dtc
+dtbs: include/config/kernel.release scripts_dtc
 	$(Q)$(MAKE) $(build)=$(dtstree)
 
+ifneq ($(filter dtbs_check, $(MAKECMDGOALS)),)
+dtbs: dt_binding_check
+endif
+
 dtbs_check: export CHECK_DTBS=1
-dtbs_check: dt_binding_check
+dtbs_check: dtbs
 
 dtbs_install:
 	$(Q)$(MAKE) $(dtbinst)=$(dtstree)
@@ -1270,6 +1331,13 @@ ifdef CONFIG_MODULES
 
 all: modules
 
+# When we're building modules with modversions, we need to consider
+# the built-in objects during the descend as well, in order to
+# make sure the checksums are up to date before we record them.
+ifdef CONFIG_MODVERSIONS
+  KBUILD_BUILTIN := 1
+endif
+
 # Build modules
 #
 # A module can be listed more than once in obj-m resulting in
@@ -1823,3 +1891,5 @@ FORCE:
 # Declare the contents of the PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
+
+endif # dist_make

arch/Kconfig

@@ -131,6 +131,22 @@ config UPROBES
 	    managed by the kernel and kept transparent to the probed
 	    application. )
 
+config HAVE_64BIT_ALIGNED_ACCESS
+	def_bool 64BIT && !HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  Some architectures require 64 bit accesses to be 64 bit
+	  aligned, which also requires structs containing 64 bit values
+	  to be 64 bit aligned too. This includes some 32 bit
+	  architectures which can do 64 bit accesses, as well as 64 bit
+	  architectures without unaligned access.
+
+	  This symbol should be selected by an architecture if 64 bit
+	  accesses are required to be 64 bit aligned in this way even
+	  though it is not a 64 bit architecture.
+
+	  See Documentation/unaligned-memory-access.txt for more
+	  information on the topic of unaligned memory accesses.
+
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
 	help
@@ -405,6 +421,13 @@ config MMU_GATHER_NO_RANGE
 config HAVE_MMU_GATHER_NO_GATHER
 	bool
 
+config ARCH_WANT_IRQS_OFF_ACTIVATE_MM
+	bool
+	help
+	  Temporary select until all architectures can be converted to have
+	  irqs disabled over activate_mm. Architectures that do IPI based TLB
+	  shootdowns should enable this.
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 

arch/alpha/configs/defconfig

@@ -36,7 +36,6 @@ CONFIG_BLK_DEV_CY82C693=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_SCSI_AIC7XXX=m
 CONFIG_AIC7XXX_CMDS_PER_DEVICE=253
 # CONFIG_AIC7XXX_DEBUG_ENABLE is not set

arch/alpha/include/asm/io.h

@@ -322,14 +322,18 @@ static inline int __is_mmio(const volatile void __iomem *addr)
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
 extern inline unsigned int ioread8(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 	mb();
 	return ret;
 }
 
 extern inline unsigned int ioread16(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 	mb();
 	return ret;
 }
@@ -370,7 +374,9 @@ extern inline void outw(u16 b, unsigned long port)
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
 extern inline unsigned int ioread32(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
 	mb();
 	return ret;
 }
@@ -415,14 +421,18 @@ extern inline void __raw_writew(u16 b, volatile void __iomem *addr)
 
 extern inline u8 readb(const volatile void __iomem *addr)
 {
-	u8 ret = __raw_readb(addr);
+	u8 ret;
+	mb();
+	ret = __raw_readb(addr);
 	mb();
 	return ret;
 }
 
 extern inline u16 readw(const volatile void __iomem *addr)
 {
-	u16 ret = __raw_readw(addr);
+	u16 ret;
+	mb();
+	ret = __raw_readw(addr);
 	mb();
 	return ret;
 }
@@ -463,14 +473,18 @@ extern inline void __raw_writeq(u64 b, volatile void __iomem *addr)
 
 extern inline u32 readl(const volatile void __iomem *addr)
 {
-	u32 ret = __raw_readl(addr);
+	u32 ret;
+	mb();
+	ret = __raw_readl(addr);
 	mb();
 	return ret;
 }
 
 extern inline u64 readq(const volatile void __iomem *addr)
 {
-	u64 ret = __raw_readq(addr);
+	u64 ret;
+	mb();
+	ret = __raw_readq(addr);
 	mb();
 	return ret;
 }
@@ -488,10 +502,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 }
 #endif
 
-#define ioread16be(p) be16_to_cpu(ioread16(p))
+#define ioread16be(p) swab16(ioread16(p))
-#define ioread32be(p) be32_to_cpu(ioread32(p))
+#define ioread32be(p) swab32(ioread32(p))
-#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p))
+#define iowrite16be(v,p) iowrite16(swab16(v), (p))
-#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p))
+#define iowrite32be(v,p) iowrite32(swab32(v), (p))
 
 #define inb_p		inb
 #define inw_p		inw
@@ -499,14 +513,44 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 #define outb_p		outb
 #define outw_p		outw
 #define outl_p		outl
-#define readb_relaxed(addr)	__raw_readb(addr)
+
-#define readw_relaxed(addr)	__raw_readw(addr)
+extern u8 readb_relaxed(const volatile void __iomem *addr);
-#define readl_relaxed(addr)	__raw_readl(addr)
+extern u16 readw_relaxed(const volatile void __iomem *addr);
-#define readq_relaxed(addr)	__raw_readq(addr)
+extern u32 readl_relaxed(const volatile void __iomem *addr);
-#define writeb_relaxed(b, addr)	__raw_writeb(b, addr)
+extern u64 readq_relaxed(const volatile void __iomem *addr);
-#define writew_relaxed(b, addr)	__raw_writew(b, addr)
+
-#define writel_relaxed(b, addr)	__raw_writel(b, addr)
+#if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
-#define writeq_relaxed(b, addr)	__raw_writeq(b, addr)
+extern inline u8 readb_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readb(addr);
+}
+
+extern inline u16 readw_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readw(addr);
+}
+#endif
+
+#if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
+extern inline u32 readl_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readl(addr);
+}
+
+extern inline u64 readq_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readq(addr);
+}
+#endif
+
+#define writeb_relaxed	writeb
+#define writew_relaxed	writew
+#define writel_relaxed	writel
+#define writeq_relaxed	writeq
 
 /*
  * String version of IO memory access ops:

arch/alpha/include/uapi/asm/socket.h

@@ -124,6 +124,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_NETNS_COOKIE		71
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/alpha/kernel/io.c

@@ -16,21 +16,27 @@
 unsigned int
 ioread8(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 	mb();
 	return ret;
 }
 
 unsigned int ioread16(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 	mb();
 	return ret;
 }
 
 unsigned int ioread32(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
 	mb();
 	return ret;
 }
@@ -148,28 +154,36 @@ EXPORT_SYMBOL(__raw_writeq);
 
 u8 readb(const volatile void __iomem *addr)
 {
-	u8 ret = __raw_readb(addr);
+	u8 ret;
+	mb();
+	ret = __raw_readb(addr);
 	mb();
 	return ret;
 }
 
 u16 readw(const volatile void __iomem *addr)
 {
-	u16 ret = __raw_readw(addr);
+	u16 ret;
+	mb();
+	ret = __raw_readw(addr);
 	mb();
 	return ret;
 }
 
 u32 readl(const volatile void __iomem *addr)
 {
-	u32 ret = __raw_readl(addr);
+	u32 ret;
+	mb();
+	ret = __raw_readl(addr);
 	mb();
 	return ret;
 }
 
 u64 readq(const volatile void __iomem *addr)
 {
-	u64 ret = __raw_readq(addr);
+	u64 ret;
+	mb();
+	ret = __raw_readq(addr);
 	mb();
 	return ret;
 }
@@ -207,6 +221,38 @@ EXPORT_SYMBOL(writew);
 EXPORT_SYMBOL(writel);
 EXPORT_SYMBOL(writeq);
 
+/*
+ * The _relaxed functions must be ordered w.r.t. each other, but they don't
+ * have to be ordered w.r.t. other memory accesses.
+ */
+u8 readb_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readb(addr);
+}
+
+u16 readw_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readw(addr);
+}
+
+u32 readl_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readl(addr);
+}
+
+u64 readq_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readq(addr);
+}
+
+EXPORT_SYMBOL(readb_relaxed);
+EXPORT_SYMBOL(readw_relaxed);
+EXPORT_SYMBOL(readl_relaxed);
+EXPORT_SYMBOL(readq_relaxed);
 
 /*
  * Read COUNT 8-bit bytes from port PORT into memory starting at SRC.

arch/arc/Makefile

@@ -90,16 +90,22 @@ libs-y		+= arch/arc/lib/ $(LIBGCC)
 
 boot		:= arch/arc/boot
 
-#default target for make without any arguments.
+boot_targets := uImage.bin uImage.gz uImage.lzma
-KBUILD_IMAGE	:= $(boot)/bootpImage
-
-all:	bootpImage
-bootpImage: vmlinux
-
-boot_targets += uImage uImage.bin uImage.gz
 
+PHONY += $(boot_targets)
 $(boot_targets): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
+uimage-default-y			:= uImage.bin
+uimage-default-$(CONFIG_KERNEL_GZIP)	:= uImage.gz
+uimage-default-$(CONFIG_KERNEL_LZMA)	:= uImage.lzma
+
+PHONY += uImage
+uImage: $(uimage-default-y)
+	@ln -sf $< $(boot)/uImage
+	@$(kecho) '  Image $(boot)/uImage is ready'
+
+CLEAN_FILES += $(boot)/uImage
+
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)

arch/arc/boot/Makefile

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-targets := vmlinux.bin vmlinux.bin.gz uImage
+targets := vmlinux.bin vmlinux.bin.gz
 
 # uImage build relies on mkimage being availble on your host for ARC target
 # You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage
@@ -13,11 +13,6 @@ LINUX_START_TEXT = $$(readelf -h vmlinux | \
 UIMAGE_LOADADDR    = $(CONFIG_LINUX_LINK_BASE)
 UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
 
-suffix-y := bin
-suffix-$(CONFIG_KERNEL_GZIP)	:= gz
-suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
-
-targets += uImage
 targets += uImage.bin
 targets += uImage.gz
 targets += uImage.lzma
@@ -42,7 +37,3 @@ $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 
 $(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
 	$(call if_changed,uimage,lzma)
-
-$(obj)/uImage: $(obj)/uImage.$(suffix-y)
-	@ln -sf $(notdir $<) $@
-	@echo '  Image $@ is ready'

arch/arc/boot/dts/axc001.dtsi

@@ -85,7 +85,7 @@
 	 * avoid duplicating the MB dtsi file given that IRQ from
 	 * this intc to cpu intc are different for axs101 and axs103
 	 */
-	mb_intc: dw-apb-ictl@e0012000 {
+	mb_intc: interrupt-controller@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0x0 0xe0012000 0x0 0x200 >;

arch/arc/boot/dts/axc003.dtsi

@@ -129,7 +129,7 @@
 	 * avoid duplicating the MB dtsi file given that IRQ from
 	 * this intc to cpu intc are different for axs101 and axs103
 	 */
-	mb_intc: dw-apb-ictl@e0012000 {
+	mb_intc: interrupt-controller@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0x0 0xe0012000 0x0 0x200 >;

arch/arc/boot/dts/axc003_idu.dtsi

@@ -135,7 +135,7 @@
 	 * avoid duplicating the MB dtsi file given that IRQ from
 	 * this intc to cpu intc are different for axs101 and axs103
 	 */
-	mb_intc: dw-apb-ictl@e0012000 {
+	mb_intc: interrupt-controller@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0x0 0xe0012000 0x0 0x200 >;

arch/arc/boot/dts/hsdk.dts

@@ -88,6 +88,8 @@
 
 	arcpct: pct {
 		compatible = "snps,archs-pct";
+		interrupt-parent = <&cpu_intc>;
+		interrupts = <20>;
 	};
 
 	/* TIMER0 with interrupt for clockevent */
@@ -208,7 +210,7 @@
 			reg = <0x8000 0x2000>;
 			interrupts = <10>;
 			interrupt-names = "macirq";
-			phy-mode = "rgmii";
+			phy-mode = "rgmii-id";
 			snps,pbl = <32>;
 			snps,multicast-filter-bins = <256>;
 			clocks = <&gmacclk>;
@@ -226,7 +228,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "snps,dwmac-mdio";
-				phy0: ethernet-phy@0 {
+				phy0: ethernet-phy@0 { /* Micrel KSZ9031 */
 					reg = <0>;
 				};
 			};

arch/arc/boot/dts/vdk_axc003.dtsi

@@ -46,7 +46,7 @@
 
 	};
 
-	mb_intc: dw-apb-ictl@e0012000 {
+	mb_intc: interrupt-controller@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0xe0012000 0x200 >;

arch/arc/boot/dts/vdk_axc003_idu.dtsi

@@ -54,7 +54,7 @@
 
 	};
 
-	mb_intc: dw-apb-ictl@e0012000 {
+	mb_intc: interrupt-controller@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0xe0012000 0x200 >;

arch/arc/include/asm/elf.h

@@ -19,7 +19,7 @@
 #define  R_ARC_32_PCREL		0x31
 
 /*to set parameters in the core dumps */
-#define ELF_ARCH		EM_ARCOMPACT
+#define ELF_ARCH		EM_ARC_INUSE
 #define ELF_CLASS		ELFCLASS32
 
 #ifdef CONFIG_CPU_BIG_ENDIAN

arch/arc/include/asm/page.h

@@ -10,6 +10,7 @@
 #ifndef __ASSEMBLY__
 
 #define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 #define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
 
 struct vm_area_struct;

arch/arc/include/asm/pgtable.h

@@ -135,8 +135,10 @@
 
 #ifdef CONFIG_ARC_HAS_PAE40
 #define PTE_BITS_NON_RWX_IN_PD1	(0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE)
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
 #else
 #define PTE_BITS_NON_RWX_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE)
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
 #endif
 
 /**************************************************************************

arch/arc/kernel/entry.S

@@ -153,7 +153,6 @@ END(EV_Extension)
 tracesys:
 	; save EFA in case tracer wants the PC of traced task
 	; using ERET won't work since next-PC has already committed
-	lr  r12, [efa]
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
 	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
 
@@ -196,15 +195,9 @@ tracesys_exit:
 ; Breakpoint TRAP
 ; ---------------------------------------------
 trap_with_param:
-
+	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
-	; stop_pc info by gdb needs this info
-	lr  r0, [efa]
 	mov r1, sp
 
-	; Now that we have read EFA, it is safe to do "fake" rtie
-	;   and get out of CPU exception mode
-	FAKE_RET_FROM_EXCPN
-
 	; Save callee regs in case gdb wants to have a look
 	; SP will grow up by size of CALLEE Reg-File
 	; NOTE: clobbers r12
@@ -231,6 +224,10 @@ ENTRY(EV_Trap)
 
 	EXCEPTION_PROLOGUE
 
+	lr  r12, [efa]
+
+	FAKE_RET_FROM_EXCPN
+
 	;============ TRAP 1   :breakpoints
 	; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR)
 	bmsk.f 0, r10, 7
@@ -238,9 +235,6 @@ ENTRY(EV_Trap)
 
 	;============ TRAP  (no param): syscall top level
 
-	; First return from Exception to pure K mode (Exception/IRQs renabled)
-	FAKE_RET_FROM_EXCPN
-
 	; If syscall tracing ongoing, invoke pre-post-hooks
 	GET_CURR_THR_INFO_FLAGS   r10
 	btst r10, TIF_SYSCALL_TRACE

arch/arc/kernel/perf_event.c

@@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, has_interrupts;
+	int i, has_interrupts, irq = -1;
 	int counter_size;	/* in bits */
 
 	union cc_name {
@@ -638,22 +638,25 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	};
 
 	if (has_interrupts) {
-		int irq = platform_get_irq(pdev, 0);
+		irq = platform_get_irq(pdev, 0);
+		if (irq >= 0) {
+			int ret;
 
-		if (irq < 0) {
+			arc_pmu->irq = irq;
-			pr_err("Cannot get IRQ number for the platform\n");
+
-			return -ENODEV;
+			/* intc map function ensures irq_set_percpu_devid() called */
+			ret = request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
+						 this_cpu_ptr(&arc_pmu_cpu));
+
+			if (!ret)
+				on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
+			else
+				irq = -1;
 		}
 
-		arc_pmu->irq = irq;
+	}
 
-		/* intc map function ensures irq_set_percpu_devid() called */
+	if (irq == -1)
-		request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
-				   this_cpu_ptr(&arc_pmu_cpu));
-
-		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
-
-	} else
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
 	/*

arch/arc/kernel/setup.c

@@ -12,6 +12,7 @@
 #include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of.h>
@@ -409,12 +410,12 @@ static void arc_chk_core_config(void)
 	if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr)
 		panic("Linux built with incorrect DCCM Base address\n");
 
-	if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz)
+	if (CONFIG_ARC_DCCM_SZ * SZ_1K != cpu->dccm.sz)
 		panic("Linux built with incorrect DCCM Size\n");
 #endif
 
 #ifdef CONFIG_ARC_HAS_ICCM
-	if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz)
+	if (CONFIG_ARC_ICCM_SZ * SZ_1K != cpu->iccm.sz)
 		panic("Linux built with incorrect ICCM Size\n");
 #endif
 

arch/arc/kernel/signal.c

@@ -96,7 +96,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
-	return err;
+	return err ? -EFAULT : 0;
 }
 
 static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
@@ -110,7 +110,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 				&(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 	if (err)
-		return err;
+		return -EFAULT;
 
 	set_current_blocked(&set);
 	regs->bta	= uregs.scratch.bta;

arch/arc/kernel/stacktrace.c

@@ -38,15 +38,15 @@
 
 #ifdef CONFIG_ARC_DW2_UNWIND
 
-static void seed_unwind_frame_info(struct task_struct *tsk,
+static int
-				   struct pt_regs *regs,
+seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs,
-				   struct unwind_frame_info *frame_info)
+		       struct unwind_frame_info *frame_info)
 {
 	/*
 	 * synchronous unwinding (e.g. dump_stack)
 	 *  - uses current values of SP and friends
 	 */
-	if (tsk == NULL && regs == NULL) {
+	if (regs == NULL && (tsk == NULL || tsk == current)) {
 		unsigned long fp, sp, blink, ret;
 		frame_info->task = current;
 
@@ -65,11 +65,15 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 		frame_info->call_frame = 0;
 	} else if (regs == NULL) {
 		/*
-		 * Asynchronous unwinding of sleeping task
+		 * Asynchronous unwinding of a likely sleeping task
-		 *  - Gets SP etc from task's pt_regs (saved bottom of kernel
+		 *  - first ensure it is actually sleeping
-		 *    mode stack of task)
+		 *  - if so, it will be in __switch_to, kernel mode SP of task
+		 *    is safe-kept and BLINK at a well known location in there
 		 */
 
+		if (tsk->state == TASK_RUNNING)
+			return -1;
+
 		frame_info->task = tsk;
 
 		frame_info->regs.r27 = TSK_K_FP(tsk);
@@ -103,6 +107,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 		frame_info->regs.r63 = regs->ret;
 		frame_info->call_frame = 0;
 	}
+
+	return 0;
 }
 
 #endif
@@ -112,11 +118,12 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 		int (*consumer_fn) (unsigned int, void *), void *arg)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int ret = 0;
+	int ret = 0, cnt = 0;
 	unsigned int address;
 	struct unwind_frame_info frame_info;
 
-	seed_unwind_frame_info(tsk, regs, &frame_info);
+	if (seed_unwind_frame_info(tsk, regs, &frame_info))
+		return 0;
 
 	while (1) {
 		address = UNW_PC(&frame_info);
@@ -132,6 +139,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 			break;
 
 		frame_info.regs.r63 = frame_info.regs.r31;
+
+		if (cnt++ > 128) {
+			printk("unwinder looping too long, aborting !\n");
+			return 0;
+		}
 	}
 
 	return address;		/* return the last address it saw */

arch/arc/plat-eznps/Kconfig

@@ -6,6 +6,7 @@
 
 menuconfig ARC_PLAT_EZNPS
 	bool "\"EZchip\" ARC dev platform"
+	depends on ISA_ARCOMPACT
 	select CPU_BIG_ENDIAN
 	select CLKSRC_NPS if !PHYS_ADDR_T_64BIT
 	select EZNPS_GIC

arch/arc/plat-eznps/include/plat/ctop.h

@@ -33,7 +33,6 @@
 #define CTOP_AUX_DPC				(CTOP_AUX_BASE + 0x02C)
 #define CTOP_AUX_LPC				(CTOP_AUX_BASE + 0x030)
 #define CTOP_AUX_EFLAGS				(CTOP_AUX_BASE + 0x080)
-#define CTOP_AUX_IACK				(CTOP_AUX_BASE + 0x088)
 #define CTOP_AUX_GPA1				(CTOP_AUX_BASE + 0x08C)
 #define CTOP_AUX_UDMC				(CTOP_AUX_BASE + 0x300)
 

arch/arc/plat-hsdk/Kconfig

@@ -8,5 +8,6 @@ menuconfig ARC_SOC_HSDK
 	select ARC_HAS_ACCL_REGS
 	select ARC_IRQ_NO_AUTOSAVE
 	select CLK_HSDK
+	select RESET_CONTROLLER
 	select RESET_HSDK
 	select HAVE_PCI

arch/arm/Kconfig

@@ -507,8 +507,10 @@ config ARCH_S3C24XX
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
 	select NEED_MACH_IO_H
+	select S3C2410_WATCHDOG
 	select SAMSUNG_ATAGS
 	select USE_OF
+	select WATCHDOG
 	help
 	  Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443
 	  and S3C2450 SoCs based systems, such as the Simtec Electronics BAST

arch/arm/boot/compressed/Makefile

@@ -121,9 +121,9 @@ ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
-KBSS_SZ = $(shell echo $$(($$($(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
+KBSS_SZ = $(shell echo $$(($$($(NM) $(obj)/../../../../vmlinux | \
-		sed -n -e 's/^\([^ ]*\) [AB] __bss_start$$/-0x\1/p' \
+		sed -n -e 's/^\([^ ]*\) [ABD] __bss_start$$/-0x\1/p' \
-		       -e 's/^\([^ ]*\) [AB] __bss_stop$$/+0x\1/p') )) )
+		       -e 's/^\([^ ]*\) [ABD] __bss_stop$$/+0x\1/p') )) )
 LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)
@@ -165,7 +165,7 @@ $(obj)/bswapsdi2.S: $(srctree)/arch/$(SRCARCH)/lib/bswapsdi2.S
 # The .data section is already discarded by the linker script so no need
 # to bother about it here.
 check_for_bad_syms = \
-bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \
+bad_syms=$$($(NM) $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \
 [ -z "$$bad_syms" ] || \
   ( echo "following symbols must have non local/private scope:" >&2; \
     echo "$$bad_syms" >&2; false )

arch/arm/boot/compressed/head.S

@@ -1142,9 +1142,9 @@ __armv4_mmu_cache_off:
 __armv7_mmu_cache_off:
 		mrc	p15, 0, r0, c1, c0
 #ifdef CONFIG_MMU
-		bic	r0, r0, #0x000d
+		bic	r0, r0, #0x0005
 #else
-		bic	r0, r0, #0x000c
+		bic	r0, r0, #0x0004
 #endif
 		mcr	p15, 0, r0, c1, c0	@ turn MMU and cache off
 		mov	r12, lr

arch/arm/boot/compressed/vmlinux.lds.S

@@ -43,7 +43,7 @@ SECTIONS
   }
   .table : ALIGN(4) {
     _table_start = .;
-    LONG(ZIMAGE_MAGIC(2))
+    LONG(ZIMAGE_MAGIC(4))
     LONG(ZIMAGE_MAGIC(0x5a534c4b))
     LONG(ZIMAGE_MAGIC(__piggy_size_addr - _start))
     LONG(ZIMAGE_MAGIC(_kernel_bss_size))

arch/arm/boot/deflate_xip_data.sh

@@ -56,7 +56,7 @@ trap 'rm -f "$XIPIMAGE.tmp"; exit 1' 1 2 3
 # substitute the data section by a compressed version
 $DD if="$XIPIMAGE" count=$data_start iflag=count_bytes of="$XIPIMAGE.tmp"
 $DD if="$XIPIMAGE"  skip=$data_start iflag=skip_bytes |
-gzip -9 >> "$XIPIMAGE.tmp"
+$KGZIP -9 >> "$XIPIMAGE.tmp"
 
 # replace kernel binary
 mv -f "$XIPIMAGE.tmp" "$XIPIMAGE"

arch/arm/boot/dts/am335x-pocketbeagle.dts

@@ -88,7 +88,6 @@
 			AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0)
-			AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4)		/* (B12) mcasp0_aclkr.mmc0_sdwp */
 		>;
 	};
 

arch/arm/boot/dts/am33xx.dtsi

@@ -40,6 +40,9 @@
 		ethernet1 = &cpsw_emac1;
 		spi0 = &spi0;
 		spi1 = &spi1;
+		mmc0 = &mmc1;
+		mmc1 = &mmc2;
+		mmc2 = &mmc3;
 	};
 
 	cpus {

arch/arm/boot/dts/am437x-l4.dtsi

@@ -1576,8 +1576,9 @@
 			reg-names = "rev";
 			ti,hwmods = "d_can0";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>;
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>,
-			clock-names = "fck";
+			<&dcan0_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xcc000 0x2000>;
@@ -1585,6 +1586,8 @@
 			dcan0: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan0_fck>;
+				clock-names = "fck";
 				syscon-raminit = <&scm_conf 0x644 0>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
@@ -1597,8 +1600,9 @@
 			reg-names = "rev";
 			ti,hwmods = "d_can1";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>;
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>,
-			clock-names = "fck";
+			<&dcan1_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xd0000 0x2000>;
@@ -1606,6 +1610,8 @@
 			dcan1: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan1_fck>;
+				clock-name = "fck";
 				syscon-raminit = <&scm_conf 0x644 1>;
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";

arch/arm/boot/dts/armada-385-turris-omnia.dts

@@ -236,6 +236,7 @@
 		status = "okay";
 		compatible = "ethernet-phy-id0141.0DD1", "ethernet-phy-ieee802.3-c22";
 		reg = <1>;
+		marvell,reg-init = <3 18 0 0x4985>;
 
 		/* irq is connected to &pcawan pin 7 */
 	};

arch/arm/boot/dts/armada-388-helios4.dts

@@ -70,6 +70,9 @@
 
 	system-leds {
 		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&helios_system_led_pins>;
+
 		status-led {
 			label = "helios4:green:status";
 			gpios = <&gpio0 24 GPIO_ACTIVE_LOW>;
@@ -86,6 +89,9 @@
 
 	io-leds {
 		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&helios_io_led_pins>;
+
 		sata1-led {
 			label = "helios4:green:ata1";
 			gpios = <&gpio1 17 GPIO_ACTIVE_LOW>;
@@ -121,11 +127,15 @@
 	fan1: j10-pwm {
 		compatible = "pwm-fan";
 		pwms = <&gpio1 9 40000>;	/* Target freq:25 kHz */
+		pinctrl-names = "default";
+		pinctrl-0 = <&helios_fan1_pins>;
 	};
 
 	fan2: j17-pwm {
 		compatible = "pwm-fan";
 		pwms = <&gpio1 23 40000>;	/* Target freq:25 kHz */
+		pinctrl-names = "default";
+		pinctrl-0 = <&helios_fan2_pins>;
 	};
 
 	usb2_phy: usb2-phy {
@@ -291,16 +301,22 @@
 						       "mpp39", "mpp40";
 					marvell,function = "sd0";
 				};
-				helios_led_pins: helios-led-pins {
+				helios_system_led_pins: helios-system-led-pins {
-					marvell,pins = "mpp24", "mpp25",
+					marvell,pins = "mpp24", "mpp25";
-						       "mpp49", "mpp50",
+					marvell,function = "gpio";
+				};
+				helios_io_led_pins: helios-io-led-pins {
+					marvell,pins = "mpp49", "mpp50",
 						       "mpp52", "mpp53",
 						       "mpp54";
 					marvell,function = "gpio";
 				};
-				helios_fan_pins: helios-fan-pins {
+				helios_fan1_pins: helios_fan1_pins {
-					marvell,pins = "mpp41", "mpp43",
+					marvell,pins = "mpp41", "mpp43";
-						       "mpp48", "mpp55";
+					marvell,function = "gpio";
+				};
+				helios_fan2_pins: helios_fan2_pins {
+					marvell,pins = "mpp48", "mpp55";
 					marvell,function = "gpio";
 				};
 				microsom_spi1_cs_pins: spi1-cs-pins {

arch/arm/boot/dts/armada-38x.dtsi

@@ -339,7 +339,8 @@
 
 			comphy: phy@18300 {
 				compatible = "marvell,armada-380-comphy";
-				reg = <0x18300 0x100>;
+				reg-names = "comphy", "conf";
+				reg = <0x18300 0x100>, <0x18460 4>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 

arch/arm/boot/dts/armada-xp-98dx3236.dtsi

@@ -266,11 +266,6 @@
 	reg = <0x11000 0x100>;
 };
 
-&i2c1 {
-	compatible = "marvell,mv78230-i2c", "marvell,mv64xxx-i2c";
-	reg = <0x11100 0x100>;
-};
-
 &mpic {
 	reg = <0x20a00 0x2d0>, <0x21070 0x58>;
 };

arch/arm/boot/dts/aspeed-bmc-facebook-tiogapass.dts

@@ -81,11 +81,6 @@
 	status = "okay";
 };
 
-&vuart {
-	// VUART Host Console
-	status = "okay";
-};
-
 &uart1 {
 	// Host Console
 	status = "okay";

arch/arm/boot/dts/aspeed-bmc-intel-s2600wf.dts

@@ -22,9 +22,9 @@
 		#size-cells = <1>;
 		ranges;
 
-		vga_memory: framebuffer@7f000000 {
+		vga_memory: framebuffer@9f000000 {
 			no-map;
-			reg = <0x7f000000 0x01000000>;
+			reg = <0x9f000000 0x01000000>; /* 16M */
 		};
 	};
 

arch/arm/boot/dts/aspeed-g4.dtsi

@@ -371,6 +371,7 @@
 						compatible = "aspeed,ast2400-ibt-bmc";
 						reg = <0xc0 0x18>;
 						interrupts = <8>;
+						clocks = <&syscon ASPEED_CLK_GATE_LCLK>;
 						status = "disabled";
 					};
 				};

arch/arm/boot/dts/aspeed-g5.dtsi

@@ -464,6 +464,7 @@
 						compatible = "aspeed,ast2500-ibt-bmc";
 						reg = <0xc0 0x18>;
 						interrupts = <8>;
+						clocks = <&syscon ASPEED_CLK_GATE_LCLK>;
 						status = "disabled";
 					};
 				};

arch/arm/boot/dts/at91-sama5d27_som1.dtsi

@@ -44,8 +44,8 @@
 				pinctrl-0 = <&pinctrl_macb0_default>;
 				phy-mode = "rmii";
 
-				ethernet-phy@0 {
+				ethernet-phy@7 {
-					reg = <0x0>;
+					reg = <0x7>;
 					interrupt-parent = <&pioA>;
 					interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>;
 					pinctrl-names = "default";

arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts

@@ -40,7 +40,7 @@
 
 	ahb {
 		usb0: gadget@300000 {
-			atmel,vbus-gpio = <&pioA PIN_PA27 GPIO_ACTIVE_HIGH>;
+			atmel,vbus-gpio = <&pioA PIN_PB11 GPIO_ACTIVE_HIGH>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usba_vbus>;
 			status = "okay";
@@ -125,8 +125,6 @@
 			bus-width = <8>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_sdmmc0_default>;
-			non-removable;
-			mmc-ddr-1_8v;
 			status = "okay";
 		};
 

arch/arm/boot/dts/at91-sama5d3_xplained.dts

@@ -242,6 +242,11 @@
 						atmel,pins =
 							<AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>;	/* PE9, conflicts with A9 */
 					};
+					pinctrl_usb_default: usb_default {
+						atmel,pins =
+							<AT91_PIOE 3 AT91_PERIPH_GPIO AT91_PINCTRL_NONE
+							 AT91_PIOE 4 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>;
+					};
 				};
 			};
 		};
@@ -259,6 +264,8 @@
 					   &pioE 3 GPIO_ACTIVE_LOW
 					   &pioE 4 GPIO_ACTIVE_LOW
 					  >;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_usb_default>;
 			status = "okay";
 		};